├── README.md
├── figures
├── component.png
├── e-step.png
├── m-step.png
└── problem.png
├── semisupervised
├── codes
│ ├── gnn.py
│ ├── layer.py
│ ├── loader.py
│ ├── run_citeseer.py
│ ├── run_cora.py
│ ├── run_pubmed.py
│ ├── train.py
│ └── trainer.py
└── data
│ ├── citeseer
│ ├── dev.txt
│ ├── feature.txt
│ ├── label.txt
│ ├── net.txt
│ ├── test.txt
│ └── train.txt
│ ├── cora
│ ├── dev.txt
│ ├── feature.txt
│ ├── label.txt
│ ├── net.txt
│ ├── test.txt
│ └── train.txt
│ └── pubmed
│ ├── dev.txt
│ ├── feature.txt
│ ├── label.txt
│ ├── net.txt
│ ├── test.txt
│ └── train.txt
└── unsupervised
├── codes
├── gnn.py
├── layer.py
├── loader.py
├── run_citeseer.py
├── run_cora.py
├── train.py
└── trainer.py
└── data
├── citeseer
├── dev.txt
├── feature.txt
├── label.true
├── label.txt
├── net.txt
├── test.txt
├── train.true
└── train.txt
└── cora
├── dev.txt
├── feature.txt
├── label.true
├── label.txt
├── net.txt
├── test.txt
├── train.true
└── train.txt
/README.md:
--------------------------------------------------------------------------------
1 | # GMNN
2 | This is an implementation of the [GMNN (Graph Markov Neural Networks)](https://arxiv.org/abs/1905.06214) model.
3 |
4 | Table of Contents
5 | =================
6 |
7 | * [Introduction](#introduction)
8 | * [Illustration](#illustration)
9 | * [Semi-supervised Object Classification](#Semi-supervised-Object-Classification)
10 | * [Two Graph Neural Networks](#Two-Graph-Neural-Networks)
11 | * [Optimization](#optimization)
12 | * [Data](#data)
13 | * [Usage](#usage)
14 | * [Further Improvement](#further-improvement)
15 | * [Acknowledgement](#acknowledgement)
16 | * [Citation](#citation)
17 |
18 |
19 | ## Introduction
20 | GMNN integrates **statistical relational learning methods** (e.g., relational Markov networks and Markov logic networks) and **graph neural networks** (e.g., graph convolutional networks and graph attention networks) for semi-supervised object classification. GMNN uses a conditional random field to define the joint distribution of all the object labels conditioned on object features, and the framework can be optimized with a **pseudolikelihood variational EM algorithm**, which alternates between an E-step and M-step. In the E-step, we **infer** the labels of unlabeled objects, and in the M-step, we **learn** the parameters to maximize the pseudolikelihood.
21 |
22 | To benefit training such a model, we introduce two graph neural networks in GMNN, i.e., GNNp and GNNq. GNNq is used to improve inference by learning effective object representations through **feature propagation**. GNNp is used to model local label dependency through local **label propagation**. The variational EM algorithm for optimizing GMNN is similar to the **co-training** framework. In the E-step, GNNp annotates unlabeled objects for updating GNNq, and in the M-step, GNNq annotates unlabeled objects for optimizing GNNp.
23 |
24 | GMNN can also be applied to many other applications, such as unsupervised node representation learning and link classification. In this repo, we provide codes for both **semi-supervised object classification** and **unsupervised node representation learning**.
25 |
26 | ## Illustration
27 | ### Semi-supervised Object Classification
28 | We focus on the problem of semi-supervised object classification. Given some labeled objects in a graph, we aim at classifying the unlabeled objects.
29 | 
30 |
31 | ### Two Graph Neural Networks
32 | GMNN uses two graph neural networks, one for learning object representations through feature propagation to improve inference, and the other one for modeling local label dependency through label propagation.
33 | 
34 |
35 | ### Optimization
36 | Both GNNs are optimized with the variational EM algorithm, which is similar to the co-training framework.
37 |
38 | #### E-Step
39 | 
40 |
41 | #### M-Step
42 | 
43 |
44 | ## Data
45 | For semi-supervised object classification, we provide the Cora, Citeseer and Pubmed datasets. For unsupervised node representation learning, we provide the Cora and Citeseer datasets. The datasets are constructed by [Yang et al., 2016](https://arxiv.org/abs/1603.08861), and we preprocess the datasets into our format by using the [codes](https://github.com/tkipf/gcn) from Thomas N. Kipf. Users can also use their own datasets by following the format of the provided datasets.
46 |
47 | ## Usage
48 | The codes for semi-supervised object classification can be found in the folder ```semisupervised```. The implementation corresponds to the variant ```GMNN W/o Attr. in p``` in the Table 2 of the original paper. To run the codes, go to the folder ```semisupervised/codes``` and execute ```python run_cora.py```. Then the program will print the results over 100 runs with seeds 1~100.
49 |
50 | The mean accuracy and standard deviation are summarized in the following tables:
51 |
52 | | Dataset | Cora | Citeseer | Pubmed |
53 | | -------- |----------|----------|----------|
54 | | GMNN | 83.4 (0.8) | 73.0 (0.8) | 81.3 (0.5) |
55 |
56 | The codes for unsupervised node representation learning are in the folder ```unsupervised```. The implementation corresponds to the variant ```GMNN With q and p``` in the Table 3 of the original paper. To run the codes, go to the folder ```unsupervised/codes``` and execute ```python run_cora.py```. Then the program will print the results over 50 runs.
57 |
58 | The mean accuracy and standard deviation are summarized in the following tables:
59 |
60 | | Dataset | Cora | Citeseer |
61 | | -------- |----------|----------|
62 | | GMNN | 82.6 (0.5) | 71.4 (0.5) |
63 |
64 | Note that the numbers are slightly different from those in the paper, since we make some changes to the codes before release. In addition, the above experiment was conducted with ```PyTorch 0.4.1```, and the results might be slightly different if different versions of PyTorch are used.
65 |
66 | ## Further Improvement
67 | The results reported in the previous section are not carefully tuned, and there is still a lot of room for further improvement. For example, by slightly tuning the model, the results on semi-supervised object classification can easily reach ```83.675 (Cora)```, ```73.576 (Citeseer)```, ```81.922 (Pubmed)```, as reported in the appendix of the paper. Some potential ways for further improving the results include:
68 |
69 | 1. Train the model for longer iterations.
70 |
71 | 2. Use more complicated architectures for GNNp and GNNq.
72 |
73 | 3. Use different learning rate and number of training epochs for GNNp and GNNq.
74 |
75 | 4. Draw more samples to approximate the expectation terms in objective functions.
76 |
77 | 5. Integrate GNNp and GNNq for final prediction.
78 |
79 | 6. Adjust the annealing temperature when using GNNp to annotate unlabeled objects.
80 |
81 | 7. Use more effective strategies for early stopping in training.
82 |
83 | 8. Tune the weight of the unsupervised objective function for training GNNq.
84 |
85 | ## Acknowledgement
86 | Some codes of the project are from the following repo: [pygcn](https://github.com/tkipf/pygcn).
87 |
88 | ## Citation
89 | Please consider citing the following paper if you find our codes helpful. Thank you!
90 | ```
91 | @inproceedings{qu2019gmnn,
92 | title={GMNN: Graph Markov Neural Networks},
93 | author={Qu, Meng and Bengio, Yoshua and Tang, Jian},
94 | booktitle={International Conference on Machine Learning},
95 | pages={5241--5250},
96 | year={2019}
97 | }
98 | ```
99 |
100 |
101 |
--------------------------------------------------------------------------------
/figures/component.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DeepGraphLearning/GMNN/e8a2232bca60b8b6a43e97a9c5d8121ed83780a1/figures/component.png
--------------------------------------------------------------------------------
/figures/e-step.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DeepGraphLearning/GMNN/e8a2232bca60b8b6a43e97a9c5d8121ed83780a1/figures/e-step.png
--------------------------------------------------------------------------------
/figures/m-step.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DeepGraphLearning/GMNN/e8a2232bca60b8b6a43e97a9c5d8121ed83780a1/figures/m-step.png
--------------------------------------------------------------------------------
/figures/problem.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/DeepGraphLearning/GMNN/e8a2232bca60b8b6a43e97a9c5d8121ed83780a1/figures/problem.png
--------------------------------------------------------------------------------
/semisupervised/codes/gnn.py:
--------------------------------------------------------------------------------
1 | import math
2 | import numpy as np
3 | import torch
4 | from torch import nn
5 | from torch.nn import init
6 | from torch.autograd import Variable
7 | import torch.nn.functional as F
8 | from layer import GraphConvolution
9 |
10 | class GNNq(nn.Module):
11 | def __init__(self, opt, adj):
12 | super(GNNq, self).__init__()
13 | self.opt = opt
14 | self.adj = adj
15 |
16 | opt_ = dict([('in', opt['num_feature']), ('out', opt['hidden_dim'])])
17 | self.m1 = GraphConvolution(opt_, adj)
18 |
19 | opt_ = dict([('in', opt['hidden_dim']), ('out', opt['num_class'])])
20 | self.m2 = GraphConvolution(opt_, adj)
21 |
22 | if opt['cuda']:
23 | self.cuda()
24 |
25 | def reset(self):
26 | self.m1.reset_parameters()
27 | self.m2.reset_parameters()
28 |
29 | def forward(self, x):
30 | x = F.dropout(x, self.opt['input_dropout'], training=self.training)
31 | x = self.m1(x)
32 | x = F.relu(x)
33 | x = F.dropout(x, self.opt['dropout'], training=self.training)
34 | x = self.m2(x)
35 | return x
36 |
37 | class GNNp(nn.Module):
38 | def __init__(self, opt, adj):
39 | super(GNNp, self).__init__()
40 | self.opt = opt
41 | self.adj = adj
42 |
43 | opt_ = dict([('in', opt['num_class']), ('out', opt['hidden_dim'])])
44 | self.m1 = GraphConvolution(opt_, adj)
45 |
46 | opt_ = dict([('in', opt['hidden_dim']), ('out', opt['num_class'])])
47 | self.m2 = GraphConvolution(opt_, adj)
48 |
49 | if opt['cuda']:
50 | self.cuda()
51 |
52 | def reset(self):
53 | self.m1.reset_parameters()
54 | self.m2.reset_parameters()
55 |
56 | def forward(self, x):
57 | x = F.dropout(x, self.opt['input_dropout'], training=self.training)
58 | x = self.m1(x)
59 | x = F.relu(x)
60 | x = F.dropout(x, self.opt['dropout'], training=self.training)
61 | x = self.m2(x)
62 | return x
63 |
--------------------------------------------------------------------------------
/semisupervised/codes/layer.py:
--------------------------------------------------------------------------------
1 | import math
2 | import numpy as np
3 | import torch
4 | from torch import nn
5 | from torch.nn import init
6 | from torch.autograd import Variable
7 | import torch.nn.functional as F
8 | from torch.nn.parameter import Parameter
9 |
10 | class GraphConvolution(nn.Module):
11 |
12 | def __init__(self, opt, adj):
13 | super(GraphConvolution, self).__init__()
14 | self.opt = opt
15 | self.in_size = opt['in']
16 | self.out_size = opt['out']
17 | self.adj = adj
18 | self.weight = Parameter(torch.Tensor(self.in_size, self.out_size))
19 | self.reset_parameters()
20 |
21 | def reset_parameters(self):
22 | stdv = 1. / math.sqrt(self.out_size)
23 | self.weight.data.uniform_(-stdv, stdv)
24 |
25 | def forward(self, x):
26 | m = torch.mm(x, self.weight)
27 | m = torch.spmm(self.adj, m)
28 | return m
29 |
--------------------------------------------------------------------------------
/semisupervised/codes/loader.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import math
4 | import numpy as np
5 | import torch
6 | from torch.autograd import Variable
7 |
8 | class Vocab(object):
9 |
10 | def __init__(self, file_name, cols, with_padding=False):
11 | self.itos = []
12 | self.stoi = {}
13 | self.vocab_size = 0
14 |
15 | if with_padding:
16 | string = ''
17 | self.stoi[string] = self.vocab_size
18 | self.itos.append(string)
19 | self.vocab_size += 1
20 |
21 | fi = open(file_name, 'r')
22 | for line in fi:
23 | items = line.strip().split('\t')
24 | for col in cols:
25 | item = items[col]
26 | strings = item.strip().split(' ')
27 | for string in strings:
28 | string = string.split(':')[0]
29 | if string not in self.stoi:
30 | self.stoi[string] = self.vocab_size
31 | self.itos.append(string)
32 | self.vocab_size += 1
33 | fi.close()
34 |
35 | def __len__(self):
36 | return self.vocab_size
37 |
38 | class EntityLabel(object):
39 |
40 | def __init__(self, file_name, entity, label):
41 | self.vocab_n, self.col_n = entity
42 | self.vocab_l, self.col_l = label
43 | self.itol = [-1 for k in range(self.vocab_n.vocab_size)]
44 |
45 | fi = open(file_name, 'r')
46 | for line in fi:
47 | items = line.strip().split('\t')
48 | sn, sl = items[self.col_n], items[self.col_l]
49 | n = self.vocab_n.stoi.get(sn, -1)
50 | l = self.vocab_l.stoi.get(sl, -1)
51 | if n == -1:
52 | continue
53 | self.itol[n] = l
54 | fi.close()
55 |
56 | class EntityFeature(object):
57 |
58 | def __init__(self, file_name, entity, feature):
59 | self.vocab_n, self.col_n = entity
60 | self.vocab_f, self.col_f = feature
61 | self.itof = [[] for k in range(len(self.vocab_n))]
62 | self.one_hot = []
63 |
64 | fi = open(file_name, 'r')
65 | for line in fi:
66 | items = line.strip().split('\t')
67 | sn, sf = items[self.col_n], items[self.col_f]
68 | n = self.vocab_n.stoi.get(sn, -1)
69 | if n == -1:
70 | continue
71 | for s in sf.strip().split(' '):
72 | f = self.vocab_f.stoi.get(s.split(':')[0], -1)
73 | w = float(s.split(':')[1])
74 | if f == -1:
75 | continue
76 | self.itof[n].append((f, w))
77 | fi.close()
78 |
79 | def to_one_hot(self, binary=False):
80 | self.one_hot = [[0 for j in range(len(self.vocab_f))] for i in range(len(self.vocab_n))]
81 | for k in range(len(self.vocab_n)):
82 | sm = 0
83 | for fid, wt in self.itof[k]:
84 | if binary:
85 | wt = 1.0
86 | sm += wt
87 | for fid, wt in self.itof[k]:
88 | if binary:
89 | wt = 1.0
90 | self.one_hot[k][fid] = wt / sm
91 |
92 | class Graph(object):
93 | def __init__(self, file_name, entity, weight=None):
94 | self.vocab_n, self.col_u, self.col_v = entity
95 | self.col_w = weight
96 | self.edges = []
97 |
98 | self.node_size = -1
99 |
100 | self.eid2iid = None
101 | self.iid2eid = None
102 |
103 | self.adj_w = None
104 | self.adj_t = None
105 |
106 | with open(file_name, 'r') as fi:
107 |
108 | for line in fi:
109 | items = line.strip().split('\t')
110 |
111 | su, sv = items[self.col_u], items[self.col_v]
112 | sw = items[self.col_w] if self.col_w != None else None
113 |
114 | u, v = self.vocab_n.stoi.get(su, -1), self.vocab_n.stoi.get(sv, -1)
115 | w = float(sw) if sw != None else 1
116 |
117 | if u == -1 or v == -1 or w <= 0:
118 | continue
119 |
120 | self.edges += [(u, v, w)]
121 |
122 | def get_node_size(self):
123 | return self.node_size
124 |
125 | def get_edge_size(self):
126 | return len(self.edges)
127 |
128 | def to_symmetric(self, self_link_weight=1.0):
129 | vocab = set()
130 | for u, v, w in self.edges:
131 | vocab.add(u)
132 | vocab.add(v)
133 |
134 | pair2wt = dict()
135 | for u, v, w in self.edges:
136 | pair2wt[(u, v)] = w
137 |
138 | edges_ = list()
139 | for (u, v), w in pair2wt.items():
140 | if u == v:
141 | continue
142 | w_ = pair2wt.get((v, u), -1)
143 | if w > w_:
144 | edges_ += [(u, v, w), (v, u, w)]
145 | elif w == w_:
146 | edges_ += [(u, v, w)]
147 | for k in vocab:
148 | edges_ += [(k, k, self_link_weight)]
149 |
150 | d = dict()
151 | for u, v, w in edges_:
152 | d[u] = d.get(u, 0.0) + w
153 |
154 | self.edges = [(u, v, w/math.sqrt(d[u]*d[v])) for u, v, w in edges_]
155 |
156 | def get_sparse_adjacency(self, cuda=True):
157 | shape = torch.Size([self.vocab_n.vocab_size, self.vocab_n.vocab_size])
158 |
159 | us, vs, ws = [], [], []
160 | for u, v, w in self.edges:
161 | us += [u]
162 | vs += [v]
163 | ws += [w]
164 | index = torch.LongTensor([us, vs])
165 | value = torch.Tensor(ws)
166 | if cuda:
167 | index = index.cuda()
168 | value = value.cuda()
169 | adj = torch.sparse.FloatTensor(index, value, shape)
170 | if cuda:
171 | adj = adj.cuda()
172 |
173 | return adj
174 |
--------------------------------------------------------------------------------
/semisupervised/codes/run_citeseer.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import copy
4 | import json
5 | import datetime
6 |
7 | opt = dict()
8 |
9 | opt['dataset'] = '../data/citeseer'
10 | opt['hidden_dim'] = 16
11 | opt['input_dropout'] = 0.5
12 | opt['dropout'] = 0
13 | opt['optimizer'] = 'rmsprop'
14 | opt['lr'] = 0.05
15 | opt['decay'] = 5e-4
16 | opt['self_link_weight'] = 1.0
17 | opt['pre_epoch'] = 200
18 | opt['epoch'] = 100
19 | opt['iter'] = 1
20 | opt['use_gold'] = 1
21 | opt['draw'] = 'smp'
22 | opt['tau'] = 0.1
23 |
24 | def generate_command(opt):
25 | cmd = 'python3 train.py'
26 | for opt, val in opt.items():
27 | cmd += ' --' + opt + ' ' + str(val)
28 | return cmd
29 |
30 | def run(opt):
31 | opt_ = copy.deepcopy(opt)
32 | os.system(generate_command(opt_))
33 |
34 | for k in range(100):
35 | seed = k + 1
36 | opt['seed'] = seed
37 | run(opt)
38 |
--------------------------------------------------------------------------------
/semisupervised/codes/run_cora.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import copy
4 | import json
5 | import datetime
6 |
7 | opt = dict()
8 |
9 | opt['dataset'] = '../data/cora'
10 | opt['hidden_dim'] = 16
11 | opt['input_dropout'] = 0.5
12 | opt['dropout'] = 0
13 | opt['optimizer'] = 'rmsprop'
14 | opt['lr'] = 0.05
15 | opt['decay'] = 5e-4
16 | opt['self_link_weight'] = 1.0
17 | opt['pre_epoch'] = 100
18 | opt['epoch'] = 100
19 | opt['iter'] = 1
20 | opt['use_gold'] = 1
21 | opt['draw'] = 'smp'
22 | opt['tau'] = 0.1
23 |
24 | def generate_command(opt):
25 | cmd = 'python3 train.py'
26 | for opt, val in opt.items():
27 | cmd += ' --' + opt + ' ' + str(val)
28 | return cmd
29 |
30 | def run(opt):
31 | opt_ = copy.deepcopy(opt)
32 | os.system(generate_command(opt_))
33 |
34 | for k in range(100):
35 | seed = k + 1
36 | opt['seed'] = seed
37 | run(opt)
38 |
--------------------------------------------------------------------------------
/semisupervised/codes/run_pubmed.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import copy
4 | import json
5 | import datetime
6 |
7 | opt = dict()
8 |
9 | opt['dataset'] = '../data/pubmed'
10 | opt['hidden_dim'] = 16
11 | opt['input_dropout'] = 0.5
12 | opt['dropout'] = 0
13 | opt['optimizer'] = 'adam'
14 | opt['lr'] = 0.01
15 | opt['decay'] = 5e-4
16 | opt['self_link_weight'] = 1.0
17 | opt['pre_epoch'] = 200
18 | opt['epoch'] = 100
19 | opt['iter'] = 1
20 | opt['use_gold'] = 1
21 | opt['draw'] = 'smp'
22 | opt['tau'] = 0.1
23 |
24 | def generate_command(opt):
25 | cmd = 'python3 train.py'
26 | for opt, val in opt.items():
27 | cmd += ' --' + opt + ' ' + str(val)
28 | return cmd
29 |
30 | def run(opt):
31 | opt_ = copy.deepcopy(opt)
32 | os.system(generate_command(opt_))
33 |
34 | for k in range(100):
35 | seed = k + 1
36 | opt['seed'] = seed
37 | run(opt)
38 |
--------------------------------------------------------------------------------
/semisupervised/codes/train.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import copy
4 | from datetime import datetime
5 | import time
6 | import numpy as np
7 | import random
8 | import argparse
9 | from shutil import copyfile
10 | import torch
11 | import torch.nn as nn
12 | import torch.optim as optim
13 | import torch.nn.functional as F
14 |
15 | from trainer import Trainer
16 | from gnn import GNNq, GNNp
17 | import loader
18 |
19 | parser = argparse.ArgumentParser()
20 | parser.add_argument('--dataset', type=str, default='data')
21 | parser.add_argument('--save', type=str, default='/')
22 | parser.add_argument('--hidden_dim', type=int, default=16, help='Hidden dimension.')
23 | parser.add_argument('--input_dropout', type=float, default=0.5, help='Input dropout rate.')
24 | parser.add_argument('--dropout', type=float, default=0.5, help='Dropout rate.')
25 | parser.add_argument('--optimizer', type=str, default='adam', help='Optimizer.')
26 | parser.add_argument('--lr', type=float, default=0.01, help='Learning rate.')
27 | parser.add_argument('--decay', type=float, default=5e-4, help='Weight decay for optimization')
28 | parser.add_argument('--self_link_weight', type=float, default=1.0, help='Weight of self-links.')
29 | parser.add_argument('--pre_epoch', type=int, default=200, help='Number of pre-training epochs.')
30 | parser.add_argument('--epoch', type=int, default=200, help='Number of training epochs per iteration.')
31 | parser.add_argument('--iter', type=int, default=10, help='Number of training iterations.')
32 | parser.add_argument('--use_gold', type=int, default=1, help='Whether using the ground-truth label of labeled objects, 1 for using, 0 for not using.')
33 | parser.add_argument('--tau', type=float, default=1.0, help='Annealing temperature in sampling.')
34 | parser.add_argument('--draw', type=str, default='max', help='Method for drawing object labels, max for max-pooling, smp for sampling.')
35 | parser.add_argument('--seed', type=int, default=1)
36 | parser.add_argument('--cuda', type=bool, default=torch.cuda.is_available())
37 | parser.add_argument('--cpu', action='store_true', help='Ignore CUDA.')
38 | args = parser.parse_args()
39 |
40 | torch.manual_seed(args.seed)
41 | np.random.seed(args.seed)
42 | random.seed(args.seed)
43 | if args.cpu:
44 | args.cuda = False
45 | elif args.cuda:
46 | torch.cuda.manual_seed(args.seed)
47 |
48 | opt = vars(args)
49 |
50 | net_file = opt['dataset'] + '/net.txt'
51 | label_file = opt['dataset'] + '/label.txt'
52 | feature_file = opt['dataset'] + '/feature.txt'
53 | train_file = opt['dataset'] + '/train.txt'
54 | dev_file = opt['dataset'] + '/dev.txt'
55 | test_file = opt['dataset'] + '/test.txt'
56 |
57 | vocab_node = loader.Vocab(net_file, [0, 1])
58 | vocab_label = loader.Vocab(label_file, [1])
59 | vocab_feature = loader.Vocab(feature_file, [1])
60 |
61 | opt['num_node'] = len(vocab_node)
62 | opt['num_feature'] = len(vocab_feature)
63 | opt['num_class'] = len(vocab_label)
64 |
65 | graph = loader.Graph(file_name=net_file, entity=[vocab_node, 0, 1])
66 | label = loader.EntityLabel(file_name=label_file, entity=[vocab_node, 0], label=[vocab_label, 1])
67 | feature = loader.EntityFeature(file_name=feature_file, entity=[vocab_node, 0], feature=[vocab_feature, 1])
68 | graph.to_symmetric(opt['self_link_weight'])
69 | feature.to_one_hot(binary=True)
70 | adj = graph.get_sparse_adjacency(opt['cuda'])
71 |
72 | with open(train_file, 'r') as fi:
73 | idx_train = [vocab_node.stoi[line.strip()] for line in fi]
74 | with open(dev_file, 'r') as fi:
75 | idx_dev = [vocab_node.stoi[line.strip()] for line in fi]
76 | with open(test_file, 'r') as fi:
77 | idx_test = [vocab_node.stoi[line.strip()] for line in fi]
78 | idx_all = list(range(opt['num_node']))
79 |
80 | inputs = torch.Tensor(feature.one_hot)
81 | target = torch.LongTensor(label.itol)
82 | idx_train = torch.LongTensor(idx_train)
83 | idx_dev = torch.LongTensor(idx_dev)
84 | idx_test = torch.LongTensor(idx_test)
85 | idx_all = torch.LongTensor(idx_all)
86 | inputs_q = torch.zeros(opt['num_node'], opt['num_feature'])
87 | target_q = torch.zeros(opt['num_node'], opt['num_class'])
88 | inputs_p = torch.zeros(opt['num_node'], opt['num_class'])
89 | target_p = torch.zeros(opt['num_node'], opt['num_class'])
90 |
91 | if opt['cuda']:
92 | inputs = inputs.cuda()
93 | target = target.cuda()
94 | idx_train = idx_train.cuda()
95 | idx_dev = idx_dev.cuda()
96 | idx_test = idx_test.cuda()
97 | idx_all = idx_all.cuda()
98 | inputs_q = inputs_q.cuda()
99 | target_q = target_q.cuda()
100 | inputs_p = inputs_p.cuda()
101 | target_p = target_p.cuda()
102 |
103 | gnnq = GNNq(opt, adj)
104 | trainer_q = Trainer(opt, gnnq)
105 |
106 | gnnp = GNNp(opt, adj)
107 | trainer_p = Trainer(opt, gnnp)
108 |
109 | def init_q_data():
110 | inputs_q.copy_(inputs)
111 | temp = torch.zeros(idx_train.size(0), target_q.size(1)).type_as(target_q)
112 | temp.scatter_(1, torch.unsqueeze(target[idx_train], 1), 1.0)
113 | target_q[idx_train] = temp
114 |
115 | def update_p_data():
116 | preds = trainer_q.predict(inputs_q, opt['tau'])
117 | if opt['draw'] == 'exp':
118 | inputs_p.copy_(preds)
119 | target_p.copy_(preds)
120 | elif opt['draw'] == 'max':
121 | idx_lb = torch.max(preds, dim=-1)[1]
122 | inputs_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
123 | target_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
124 | elif opt['draw'] == 'smp':
125 | idx_lb = torch.multinomial(preds, 1).squeeze(1)
126 | inputs_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
127 | target_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
128 | if opt['use_gold'] == 1:
129 | temp = torch.zeros(idx_train.size(0), target_q.size(1)).type_as(target_q)
130 | temp.scatter_(1, torch.unsqueeze(target[idx_train], 1), 1.0)
131 | inputs_p[idx_train] = temp
132 | target_p[idx_train] = temp
133 |
134 | def update_q_data():
135 | preds = trainer_p.predict(inputs_p)
136 | target_q.copy_(preds)
137 | if opt['use_gold'] == 1:
138 | temp = torch.zeros(idx_train.size(0), target_q.size(1)).type_as(target_q)
139 | temp.scatter_(1, torch.unsqueeze(target[idx_train], 1), 1.0)
140 | target_q[idx_train] = temp
141 |
142 | def pre_train(epoches):
143 | best = 0.0
144 | init_q_data()
145 | results = []
146 | for epoch in range(epoches):
147 | loss = trainer_q.update_soft(inputs_q, target_q, idx_train)
148 | _, preds, accuracy_dev = trainer_q.evaluate(inputs_q, target, idx_dev)
149 | _, preds, accuracy_test = trainer_q.evaluate(inputs_q, target, idx_test)
150 | results += [(accuracy_dev, accuracy_test)]
151 | if accuracy_dev > best:
152 | best = accuracy_dev
153 | state = dict([('model', copy.deepcopy(trainer_q.model.state_dict())), ('optim', copy.deepcopy(trainer_q.optimizer.state_dict()))])
154 | trainer_q.model.load_state_dict(state['model'])
155 | trainer_q.optimizer.load_state_dict(state['optim'])
156 | return results
157 |
158 | def train_p(epoches):
159 | update_p_data()
160 | results = []
161 | for epoch in range(epoches):
162 | loss = trainer_p.update_soft(inputs_p, target_p, idx_all)
163 | _, preds, accuracy_dev = trainer_p.evaluate(inputs_p, target, idx_dev)
164 | _, preds, accuracy_test = trainer_p.evaluate(inputs_p, target, idx_test)
165 | results += [(accuracy_dev, accuracy_test)]
166 | return results
167 |
168 | def train_q(epoches):
169 | update_q_data()
170 | results = []
171 | for epoch in range(epoches):
172 | loss = trainer_q.update_soft(inputs_q, target_q, idx_all)
173 | _, preds, accuracy_dev = trainer_q.evaluate(inputs_q, target, idx_dev)
174 | _, preds, accuracy_test = trainer_q.evaluate(inputs_q, target, idx_test)
175 | results += [(accuracy_dev, accuracy_test)]
176 | return results
177 |
178 | base_results, q_results, p_results = [], [], []
179 | base_results += pre_train(opt['pre_epoch'])
180 | for k in range(opt['iter']):
181 | p_results += train_p(opt['epoch'])
182 | q_results += train_q(opt['epoch'])
183 |
184 | def get_accuracy(results):
185 | best_dev, acc_test = 0.0, 0.0
186 | for d, t in results:
187 | if d > best_dev:
188 | best_dev, acc_test = d, t
189 | return acc_test
190 |
191 | acc_test = get_accuracy(q_results)
192 |
193 | print('{:.3f}'.format(acc_test * 100))
194 |
195 | if opt['save'] != '/':
196 | trainer_q.save(opt['save'] + '/gnnq.pt')
197 | trainer_p.save(opt['save'] + '/gnnp.pt')
198 |
199 |
--------------------------------------------------------------------------------
/semisupervised/codes/trainer.py:
--------------------------------------------------------------------------------
1 | import math
2 | import numpy as np
3 | import torch
4 | from torch import nn
5 | from torch.nn import init
6 | from torch.autograd import Variable
7 | import torch.nn.functional as F
8 | from torch.optim import Optimizer
9 |
10 | def get_optimizer(name, parameters, lr, weight_decay=0):
11 | if name == 'sgd':
12 | return torch.optim.SGD(parameters, lr=lr, weight_decay=weight_decay)
13 | elif name == 'rmsprop':
14 | return torch.optim.RMSprop(parameters, lr=lr, weight_decay=weight_decay)
15 | elif name == 'adagrad':
16 | return torch.optim.Adagrad(parameters, lr=lr, weight_decay=weight_decay)
17 | elif name == 'adam':
18 | return torch.optim.Adam(parameters, lr=lr, weight_decay=weight_decay)
19 | elif name == 'adamax':
20 | return torch.optim.Adamax(parameters, lr=lr, weight_decay=weight_decay)
21 | else:
22 | raise Exception("Unsupported optimizer: {}".format(name))
23 |
24 | def change_lr(optimizer, new_lr):
25 | for param_group in optimizer.param_groups:
26 | param_group['lr'] = new_lr
27 |
28 | class Trainer(object):
29 | def __init__(self, opt, model):
30 | self.opt = opt
31 | self.model = model
32 | self.criterion = nn.CrossEntropyLoss()
33 | self.parameters = [p for p in self.model.parameters() if p.requires_grad]
34 | if opt['cuda']:
35 | self.criterion.cuda()
36 | self.optimizer = get_optimizer(self.opt['optimizer'], self.parameters, self.opt['lr'], self.opt['decay'])
37 |
38 | def reset(self):
39 | self.model.reset()
40 | self.optimizer = get_optimizer(self.opt['optimizer'], self.parameters, self.opt['lr'], self.opt['decay'])
41 |
42 | def update(self, inputs, target, idx):
43 | if self.opt['cuda']:
44 | inputs = inputs.cuda()
45 | target = target.cuda()
46 | idx = idx.cuda()
47 |
48 | self.model.train()
49 | self.optimizer.zero_grad()
50 |
51 | logits = self.model(inputs)
52 | loss = self.criterion(logits[idx], target[idx])
53 |
54 | loss.backward()
55 | self.optimizer.step()
56 | return loss.item()
57 |
58 | def update_soft(self, inputs, target, idx):
59 | if self.opt['cuda']:
60 | inputs = inputs.cuda()
61 | target = target.cuda()
62 | idx = idx.cuda()
63 |
64 | self.model.train()
65 | self.optimizer.zero_grad()
66 |
67 | logits = self.model(inputs)
68 | logits = torch.log_softmax(logits, dim=-1)
69 | loss = -torch.mean(torch.sum(target[idx] * logits[idx], dim=-1))
70 |
71 | loss.backward()
72 | self.optimizer.step()
73 | return loss.item()
74 |
75 | def evaluate(self, inputs, target, idx):
76 | if self.opt['cuda']:
77 | inputs = inputs.cuda()
78 | target = target.cuda()
79 | idx = idx.cuda()
80 |
81 | self.model.eval()
82 |
83 | logits = self.model(inputs)
84 | loss = self.criterion(logits[idx], target[idx])
85 | preds = torch.max(logits[idx], dim=1)[1]
86 | correct = preds.eq(target[idx]).double()
87 | accuracy = correct.sum() / idx.size(0)
88 |
89 | return loss.item(), preds, accuracy.item()
90 |
91 | def predict(self, inputs, tau=1):
92 | if self.opt['cuda']:
93 | inputs = inputs.cuda()
94 |
95 | self.model.eval()
96 |
97 | logits = self.model(inputs) / tau
98 |
99 | logits = torch.softmax(logits, dim=-1).detach()
100 |
101 | return logits
102 |
103 | def save(self, filename):
104 | params = {
105 | 'model': self.model.state_dict(),
106 | 'optim': self.optimizer.state_dict()
107 | }
108 | try:
109 | torch.save(params, filename)
110 | except BaseException:
111 | print("[Warning: Saving failed... continuing anyway.]")
112 |
113 | def load(self, filename):
114 | try:
115 | checkpoint = torch.load(filename)
116 | except BaseException:
117 | print("Cannot load model from {}".format(filename))
118 | exit()
119 | self.model.load_state_dict(checkpoint['model'])
120 | self.optimizer.load_state_dict(checkpoint['optim'])
121 |
--------------------------------------------------------------------------------
/semisupervised/data/citeseer/dev.txt:
--------------------------------------------------------------------------------
1 | 120
2 | 121
3 | 122
4 | 123
5 | 124
6 | 125
7 | 126
8 | 127
9 | 128
10 | 129
11 | 130
12 | 131
13 | 132
14 | 133
15 | 134
16 | 135
17 | 136
18 | 137
19 | 138
20 | 139
21 | 140
22 | 141
23 | 142
24 | 143
25 | 144
26 | 145
27 | 146
28 | 147
29 | 148
30 | 149
31 | 150
32 | 151
33 | 152
34 | 153
35 | 154
36 | 155
37 | 156
38 | 157
39 | 158
40 | 159
41 | 160
42 | 161
43 | 162
44 | 163
45 | 164
46 | 165
47 | 166
48 | 167
49 | 168
50 | 169
51 | 170
52 | 171
53 | 172
54 | 173
55 | 174
56 | 175
57 | 176
58 | 177
59 | 178
60 | 179
61 | 180
62 | 181
63 | 182
64 | 183
65 | 184
66 | 185
67 | 186
68 | 187
69 | 188
70 | 189
71 | 190
72 | 191
73 | 192
74 | 193
75 | 194
76 | 195
77 | 196
78 | 197
79 | 198
80 | 199
81 | 200
82 | 201
83 | 202
84 | 203
85 | 204
86 | 205
87 | 206
88 | 207
89 | 208
90 | 209
91 | 210
92 | 211
93 | 212
94 | 213
95 | 214
96 | 215
97 | 216
98 | 217
99 | 218
100 | 219
101 | 220
102 | 221
103 | 222
104 | 223
105 | 224
106 | 225
107 | 226
108 | 227
109 | 228
110 | 229
111 | 230
112 | 231
113 | 232
114 | 233
115 | 234
116 | 235
117 | 236
118 | 237
119 | 238
120 | 239
121 | 240
122 | 241
123 | 242
124 | 243
125 | 244
126 | 245
127 | 246
128 | 247
129 | 248
130 | 249
131 | 250
132 | 251
133 | 252
134 | 253
135 | 254
136 | 255
137 | 256
138 | 257
139 | 258
140 | 259
141 | 260
142 | 261
143 | 262
144 | 263
145 | 264
146 | 265
147 | 266
148 | 267
149 | 268
150 | 269
151 | 270
152 | 271
153 | 272
154 | 273
155 | 274
156 | 275
157 | 276
158 | 277
159 | 278
160 | 279
161 | 280
162 | 281
163 | 282
164 | 283
165 | 284
166 | 285
167 | 286
168 | 287
169 | 288
170 | 289
171 | 290
172 | 291
173 | 292
174 | 293
175 | 294
176 | 295
177 | 296
178 | 297
179 | 298
180 | 299
181 | 300
182 | 301
183 | 302
184 | 303
185 | 304
186 | 305
187 | 306
188 | 307
189 | 308
190 | 309
191 | 310
192 | 311
193 | 312
194 | 313
195 | 314
196 | 315
197 | 316
198 | 317
199 | 318
200 | 319
201 | 320
202 | 321
203 | 322
204 | 323
205 | 324
206 | 325
207 | 326
208 | 327
209 | 328
210 | 329
211 | 330
212 | 331
213 | 332
214 | 333
215 | 334
216 | 335
217 | 336
218 | 337
219 | 338
220 | 339
221 | 340
222 | 341
223 | 342
224 | 343
225 | 344
226 | 345
227 | 346
228 | 347
229 | 348
230 | 349
231 | 350
232 | 351
233 | 352
234 | 353
235 | 354
236 | 355
237 | 356
238 | 357
239 | 358
240 | 359
241 | 360
242 | 361
243 | 362
244 | 363
245 | 364
246 | 365
247 | 366
248 | 367
249 | 368
250 | 369
251 | 370
252 | 371
253 | 372
254 | 373
255 | 374
256 | 375
257 | 376
258 | 377
259 | 378
260 | 379
261 | 380
262 | 381
263 | 382
264 | 383
265 | 384
266 | 385
267 | 386
268 | 387
269 | 388
270 | 389
271 | 390
272 | 391
273 | 392
274 | 393
275 | 394
276 | 395
277 | 396
278 | 397
279 | 398
280 | 399
281 | 400
282 | 401
283 | 402
284 | 403
285 | 404
286 | 405
287 | 406
288 | 407
289 | 408
290 | 409
291 | 410
292 | 411
293 | 412
294 | 413
295 | 414
296 | 415
297 | 416
298 | 417
299 | 418
300 | 419
301 | 420
302 | 421
303 | 422
304 | 423
305 | 424
306 | 425
307 | 426
308 | 427
309 | 428
310 | 429
311 | 430
312 | 431
313 | 432
314 | 433
315 | 434
316 | 435
317 | 436
318 | 437
319 | 438
320 | 439
321 | 440
322 | 441
323 | 442
324 | 443
325 | 444
326 | 445
327 | 446
328 | 447
329 | 448
330 | 449
331 | 450
332 | 451
333 | 452
334 | 453
335 | 454
336 | 455
337 | 456
338 | 457
339 | 458
340 | 459
341 | 460
342 | 461
343 | 462
344 | 463
345 | 464
346 | 465
347 | 466
348 | 467
349 | 468
350 | 469
351 | 470
352 | 471
353 | 472
354 | 473
355 | 474
356 | 475
357 | 476
358 | 477
359 | 478
360 | 479
361 | 480
362 | 481
363 | 482
364 | 483
365 | 484
366 | 485
367 | 486
368 | 487
369 | 488
370 | 489
371 | 490
372 | 491
373 | 492
374 | 493
375 | 494
376 | 495
377 | 496
378 | 497
379 | 498
380 | 499
381 | 500
382 | 501
383 | 502
384 | 503
385 | 504
386 | 505
387 | 506
388 | 507
389 | 508
390 | 509
391 | 510
392 | 511
393 | 512
394 | 513
395 | 514
396 | 515
397 | 516
398 | 517
399 | 518
400 | 519
401 | 520
402 | 521
403 | 522
404 | 523
405 | 524
406 | 525
407 | 526
408 | 527
409 | 528
410 | 529
411 | 530
412 | 531
413 | 532
414 | 533
415 | 534
416 | 535
417 | 536
418 | 537
419 | 538
420 | 539
421 | 540
422 | 541
423 | 542
424 | 543
425 | 544
426 | 545
427 | 546
428 | 547
429 | 548
430 | 549
431 | 550
432 | 551
433 | 552
434 | 553
435 | 554
436 | 555
437 | 556
438 | 557
439 | 558
440 | 559
441 | 560
442 | 561
443 | 562
444 | 563
445 | 564
446 | 565
447 | 566
448 | 567
449 | 568
450 | 569
451 | 570
452 | 571
453 | 572
454 | 573
455 | 574
456 | 575
457 | 576
458 | 577
459 | 578
460 | 579
461 | 580
462 | 581
463 | 582
464 | 583
465 | 584
466 | 585
467 | 586
468 | 587
469 | 588
470 | 589
471 | 590
472 | 591
473 | 592
474 | 593
475 | 594
476 | 595
477 | 596
478 | 597
479 | 598
480 | 599
481 | 600
482 | 601
483 | 602
484 | 603
485 | 604
486 | 605
487 | 606
488 | 607
489 | 608
490 | 609
491 | 610
492 | 611
493 | 612
494 | 613
495 | 614
496 | 615
497 | 616
498 | 617
499 | 618
500 | 619
501 |
--------------------------------------------------------------------------------
/semisupervised/data/citeseer/label.txt:
--------------------------------------------------------------------------------
1 | 0 3
2 | 1 1
3 | 2 5
4 | 3 5
5 | 4 3
6 | 5 1
7 | 6 3
8 | 7 0
9 | 8 3
10 | 9 5
11 | 10 2
12 | 11 4
13 | 12 2
14 | 13 1
15 | 14 2
16 | 15 3
17 | 16 2
18 | 17 4
19 | 18 4
20 | 19 0
21 | 20 1
22 | 21 5
23 | 22 5
24 | 23 3
25 | 24 5
26 | 25 2
27 | 26 5
28 | 27 2
29 | 28 4
30 | 29 2
31 | 30 2
32 | 31 2
33 | 32 4
34 | 33 5
35 | 34 2
36 | 35 3
37 | 36 4
38 | 37 5
39 | 38 3
40 | 39 3
41 | 40 2
42 | 41 1
43 | 42 2
44 | 43 1
45 | 44 5
46 | 45 1
47 | 46 1
48 | 47 4
49 | 48 2
50 | 49 3
51 | 50 3
52 | 51 2
53 | 52 5
54 | 53 2
55 | 54 5
56 | 55 1
57 | 56 4
58 | 57 1
59 | 58 4
60 | 59 2
61 | 60 2
62 | 61 3
63 | 62 4
64 | 63 5
65 | 64 5
66 | 65 1
67 | 66 3
68 | 67 3
69 | 68 4
70 | 69 2
71 | 70 4
72 | 71 1
73 | 72 1
74 | 73 5
75 | 74 0
76 | 75 2
77 | 76 0
78 | 77 3
79 | 78 5
80 | 79 2
81 | 80 4
82 | 81 1
83 | 82 1
84 | 83 4
85 | 84 4
86 | 85 0
87 | 86 4
88 | 87 4
89 | 88 5
90 | 89 3
91 | 90 5
92 | 91 5
93 | 92 4
94 | 93 5
95 | 94 3
96 | 95 1
97 | 96 4
98 | 97 4
99 | 98 3
100 | 99 1
101 | 100 3
102 | 101 0
103 | 102 1
104 | 103 1
105 | 104 1
106 | 105 3
107 | 106 0
108 | 107 0
109 | 108 0
110 | 109 0
111 | 110 0
112 | 111 0
113 | 112 0
114 | 113 0
115 | 114 0
116 | 115 0
117 | 116 0
118 | 117 0
119 | 118 0
120 | 119 0
121 | 120 3
122 | 121 1
123 | 122 2
124 | 123 2
125 | 124 2
126 | 125 2
127 | 126 0
128 | 127 2
129 | 128 0
130 | 129 0
131 | 130 4
132 | 131 3
133 | 132 1
134 | 133 4
135 | 134 3
136 | 135 3
137 | 136 3
138 | 137 2
139 | 138 1
140 | 139 5
141 | 140 1
142 | 141 2
143 | 142 4
144 | 143 2
145 | 144 2
146 | 145 1
147 | 146 2
148 | 147 2
149 | 148 3
150 | 149 1
151 | 150 1
152 | 151 1
153 | 152 2
154 | 153 2
155 | 154 2
156 | 155 3
157 | 156 5
158 | 157 2
159 | 158 1
160 | 159 4
161 | 160 0
162 | 161 2
163 | 162 2
164 | 163 3
165 | 164 3
166 | 165 2
167 | 166 3
168 | 167 5
169 | 168 5
170 | 169 2
171 | 170 3
172 | 171 4
173 | 172 3
174 | 173 4
175 | 174 3
176 | 175 5
177 | 176 4
178 | 177 3
179 | 178 4
180 | 179 3
181 | 180 2
182 | 181 2
183 | 182 4
184 | 183 3
185 | 184 2
186 | 185 5
187 | 186 3
188 | 187 3
189 | 188 5
190 | 189 3
191 | 190 5
192 | 191 5
193 | 192 3
194 | 193 2
195 | 194 4
196 | 195 3
197 | 196 3
198 | 197 2
199 | 198 0
200 | 199 3
201 | 200 2
202 | 201 0
203 | 202 3
204 | 203 4
205 | 204 0
206 | 205 4
207 | 206 2
208 | 207 1
209 | 208 1
210 | 209 1
211 | 210 1
212 | 211 1
213 | 212 4
214 | 213 2
215 | 214 5
216 | 215 4
217 | 216 1
218 | 217 3
219 | 218 1
220 | 219 3
221 | 220 2
222 | 221 1
223 | 222 5
224 | 223 3
225 | 224 2
226 | 225 5
227 | 226 4
228 | 227 5
229 | 228 4
230 | 229 2
231 | 230 5
232 | 231 2
233 | 232 5
234 | 233 3
235 | 234 4
236 | 235 2
237 | 236 5
238 | 237 1
239 | 238 2
240 | 239 1
241 | 240 1
242 | 241 3
243 | 242 2
244 | 243 2
245 | 244 5
246 | 245 3
247 | 246 2
248 | 247 0
249 | 248 1
250 | 249 5
251 | 250 3
252 | 251 0
253 | 252 5
254 | 253 5
255 | 254 5
256 | 255 3
257 | 256 2
258 | 257 0
259 | 258 2
260 | 259 4
261 | 260 3
262 | 261 3
263 | 262 0
264 | 263 2
265 | 264 3
266 | 265 4
267 | 266 5
268 | 267 2
269 | 268 3
270 | 269 1
271 | 270 1
272 | 271 1
273 | 272 4
274 | 273 3
275 | 274 5
276 | 275 3
277 | 276 0
278 | 277 3
279 | 278 3
280 | 279 3
281 | 280 3
282 | 281 1
283 | 282 1
284 | 283 4
285 | 284 4
286 | 285 4
287 | 286 3
288 | 287 1
289 | 288 3
290 | 289 2
291 | 290 3
292 | 291 5
293 | 292 1
294 | 293 4
295 | 294 4
296 | 295 2
297 | 296 2
298 | 297 1
299 | 298 2
300 | 299 2
301 | 300 4
302 | 301 4
303 | 302 2
304 | 303 2
305 | 304 4
306 | 305 5
307 | 306 3
308 | 307 2
309 | 308 5
310 | 309 3
311 | 310 3
312 | 311 2
313 | 312 1
314 | 313 3
315 | 314 2
316 | 315 1
317 | 316 4
318 | 317 4
319 | 318 1
320 | 319 4
321 | 320 1
322 | 321 2
323 | 322 2
324 | 323 5
325 | 324 5
326 | 325 5
327 | 326 0
328 | 327 3
329 | 328 1
330 | 329 1
331 | 330 5
332 | 331 5
333 | 332 4
334 | 333 4
335 | 334 0
336 | 335 1
337 | 336 3
338 | 337 3
339 | 338 5
340 | 339 4
341 | 340 2
342 | 341 0
343 | 342 4
344 | 343 3
345 | 344 5
346 | 345 3
347 | 346 2
348 | 347 2
349 | 348 1
350 | 349 5
351 | 350 2
352 | 351 2
353 | 352 5
354 | 353 3
355 | 354 5
356 | 355 1
357 | 356 3
358 | 357 3
359 | 358 1
360 | 359 4
361 | 360 0
362 | 361 2
363 | 362 3
364 | 363 2
365 | 364 1
366 | 365 2
367 | 366 2
368 | 367 1
369 | 368 5
370 | 369 2
371 | 370 1
372 | 371 4
373 | 372 5
374 | 373 2
375 | 374 5
376 | 375 0
377 | 376 4
378 | 377 2
379 | 378 5
380 | 379 4
381 | 380 5
382 | 381 1
383 | 382 3
384 | 383 4
385 | 384 5
386 | 385 4
387 | 386 3
388 | 387 5
389 | 388 2
390 | 389 0
391 | 390 3
392 | 391 4
393 | 392 4
394 | 393 4
395 | 394 2
396 | 395 2
397 | 396 2
398 | 397 4
399 | 398 1
400 | 399 0
401 | 400 3
402 | 401 3
403 | 402 3
404 | 403 1
405 | 404 1
406 | 405 4
407 | 406 2
408 | 407 3
409 | 408 1
410 | 409 1
411 | 410 5
412 | 411 4
413 | 412 4
414 | 413 3
415 | 414 2
416 | 415 1
417 | 416 5
418 | 417 2
419 | 418 1
420 | 419 4
421 | 420 3
422 | 421 0
423 | 422 3
424 | 423 2
425 | 424 1
426 | 425 4
427 | 426 2
428 | 427 0
429 | 428 2
430 | 429 4
431 | 430 4
432 | 431 3
433 | 432 5
434 | 433 2
435 | 434 2
436 | 435 2
437 | 436 2
438 | 437 0
439 | 438 1
440 | 439 2
441 | 440 4
442 | 441 4
443 | 442 4
444 | 443 2
445 | 444 2
446 | 445 1
447 | 446 2
448 | 447 5
449 | 448 3
450 | 449 5
451 | 450 0
452 | 451 2
453 | 452 4
454 | 453 2
455 | 454 3
456 | 455 4
457 | 456 1
458 | 457 3
459 | 458 3
460 | 459 3
461 | 460 2
462 | 461 1
463 | 462 4
464 | 463 3
465 | 464 2
466 | 465 4
467 | 466 3
468 | 467 3
469 | 468 2
470 | 469 4
471 | 470 0
472 | 471 0
473 | 472 0
474 | 473 5
475 | 474 5
476 | 475 4
477 | 476 4
478 | 477 1
479 | 478 4
480 | 479 2
481 | 480 3
482 | 481 0
483 | 482 5
484 | 483 3
485 | 484 4
486 | 485 4
487 | 486 1
488 | 487 4
489 | 488 3
490 | 489 4
491 | 490 1
492 | 491 3
493 | 492 2
494 | 493 2
495 | 494 4
496 | 495 2
497 | 496 3
498 | 497 5
499 | 498 3
500 | 499 2
501 | 500 5
502 | 501 1
503 | 502 1
504 | 503 1
505 | 504 4
506 | 505 5
507 | 506 1
508 | 507 1
509 | 508 5
510 | 509 1
511 | 510 3
512 | 511 5
513 | 512 3
514 | 513 1
515 | 514 1
516 | 515 5
517 | 516 4
518 | 517 1
519 | 518 1
520 | 519 4
521 | 520 2
522 | 521 2
523 | 522 3
524 | 523 1
525 | 524 3
526 | 525 0
527 | 526 4
528 | 527 2
529 | 528 2
530 | 529 2
531 | 530 3
532 | 531 4
533 | 532 2
534 | 533 1
535 | 534 1
536 | 535 1
537 | 536 3
538 | 537 1
539 | 538 5
540 | 539 5
541 | 540 4
542 | 541 4
543 | 542 4
544 | 543 2
545 | 544 3
546 | 545 4
547 | 546 5
548 | 547 4
549 | 548 2
550 | 549 2
551 | 550 4
552 | 551 2
553 | 552 4
554 | 553 0
555 | 554 5
556 | 555 4
557 | 556 5
558 | 557 2
559 | 558 1
560 | 559 2
561 | 560 5
562 | 561 3
563 | 562 4
564 | 563 4
565 | 564 4
566 | 565 3
567 | 566 4
568 | 567 4
569 | 568 3
570 | 569 2
571 | 570 3
572 | 571 3
573 | 572 1
574 | 573 4
575 | 574 1
576 | 575 3
577 | 576 3
578 | 577 2
579 | 578 5
580 | 579 4
581 | 580 2
582 | 581 1
583 | 582 4
584 | 583 1
585 | 584 4
586 | 585 2
587 | 586 2
588 | 587 4
589 | 588 1
590 | 589 1
591 | 590 2
592 | 591 1
593 | 592 3
594 | 593 3
595 | 594 1
596 | 595 2
597 | 596 3
598 | 597 5
599 | 598 3
600 | 599 3
601 | 600 3
602 | 601 1
603 | 602 5
604 | 603 3
605 | 604 1
606 | 605 4
607 | 606 1
608 | 607 2
609 | 608 3
610 | 609 2
611 | 610 4
612 | 611 3
613 | 612 5
614 | 613 5
615 | 614 1
616 | 615 4
617 | 616 2
618 | 617 2
619 | 618 5
620 | 619 2
621 | 2312 4
622 | 2313 5
623 | 2314 4
624 | 2315 4
625 | 2316 4
626 | 2317 1
627 | 2318 4
628 | 2319 2
629 | 2320 3
630 | 2321 3
631 | 2322 3
632 | 2323 3
633 | 2324 2
634 | 2325 3
635 | 2326 3
636 | 2327 4
637 | 2328 2
638 | 2329 0
639 | 2330 1
640 | 2331 2
641 | 2332 0
642 | 2333 3
643 | 2334 3
644 | 2335 4
645 | 2336 2
646 | 2337 4
647 | 2338 0
648 | 2339 4
649 | 2340 3
650 | 2341 3
651 | 2342 3
652 | 2343 5
653 | 2344 4
654 | 2345 5
655 | 2346 4
656 | 2347 5
657 | 2348 1
658 | 2349 1
659 | 2350 3
660 | 2351 3
661 | 2352 3
662 | 2353 3
663 | 2354 3
664 | 2355 1
665 | 2356 2
666 | 2357 3
667 | 2358 3
668 | 2359 3
669 | 2360 1
670 | 2361 2
671 | 2362 2
672 | 2363 3
673 | 2364 3
674 | 2365 1
675 | 2366 5
676 | 2367 5
677 | 2368 5
678 | 2369 3
679 | 2370 2
680 | 2371 3
681 | 2372 3
682 | 2373 3
683 | 2374 3
684 | 2375 3
685 | 2376 3
686 | 2377 3
687 | 2378 5
688 | 2379 1
689 | 2380 3
690 | 2381 1
691 | 2382 1
692 | 2383 4
693 | 2384 1
694 | 2385 3
695 | 2386 3
696 | 2387 1
697 | 2388 3
698 | 2389 3
699 | 2390 2
700 | 2391 4
701 | 2392 3
702 | 2393 3
703 | 2394 3
704 | 2395 1
705 | 2396 2
706 | 2397 2
707 | 2398 2
708 | 2399 3
709 | 2400 5
710 | 2401 2
711 | 2402 1
712 | 2403 3
713 | 2404 2
714 | 2405 2
715 | 2406 2
716 | 2408 4
717 | 2409 3
718 | 2410 3
719 | 2411 4
720 | 2412 0
721 | 2413 3
722 | 2414 1
723 | 2415 2
724 | 2416 2
725 | 2417 2
726 | 2418 2
727 | 2419 3
728 | 2420 2
729 | 2421 2
730 | 2422 2
731 | 2423 1
732 | 2424 1
733 | 2425 5
734 | 2426 2
735 | 2427 2
736 | 2428 1
737 | 2429 2
738 | 2430 4
739 | 2431 3
740 | 2432 1
741 | 2433 1
742 | 2434 3
743 | 2435 2
744 | 2436 3
745 | 2437 4
746 | 2438 3
747 | 2439 3
748 | 2440 4
749 | 2441 4
750 | 2442 3
751 | 2443 2
752 | 2444 2
753 | 2445 1
754 | 2446 3
755 | 2447 4
756 | 2448 4
757 | 2449 4
758 | 2450 4
759 | 2451 4
760 | 2452 4
761 | 2453 5
762 | 2454 0
763 | 2455 3
764 | 2456 1
765 | 2457 1
766 | 2458 3
767 | 2459 1
768 | 2460 3
769 | 2461 1
770 | 2462 3
771 | 2463 4
772 | 2464 4
773 | 2465 3
774 | 2466 2
775 | 2467 3
776 | 2468 5
777 | 2469 3
778 | 2470 3
779 | 2471 3
780 | 2472 4
781 | 2473 2
782 | 2474 2
783 | 2475 2
784 | 2476 5
785 | 2477 3
786 | 2478 1
787 | 2479 0
788 | 2480 3
789 | 2481 2
790 | 2482 5
791 | 2483 2
792 | 2484 3
793 | 2485 2
794 | 2486 4
795 | 2487 2
796 | 2488 2
797 | 2490 2
798 | 2491 0
799 | 2492 5
800 | 2493 1
801 | 2494 3
802 | 2495 4
803 | 2496 4
804 | 2497 4
805 | 2498 1
806 | 2499 1
807 | 2500 5
808 | 2501 1
809 | 2502 2
810 | 2503 0
811 | 2504 1
812 | 2505 0
813 | 2506 2
814 | 2507 2
815 | 2508 3
816 | 2509 3
817 | 2510 3
818 | 2511 3
819 | 2512 5
820 | 2513 4
821 | 2514 4
822 | 2515 3
823 | 2516 1
824 | 2517 1
825 | 2518 2
826 | 2519 1
827 | 2520 2
828 | 2521 2
829 | 2522 2
830 | 2523 2
831 | 2524 5
832 | 2525 0
833 | 2526 1
834 | 2527 2
835 | 2528 2
836 | 2529 4
837 | 2530 0
838 | 2531 4
839 | 2532 1
840 | 2533 1
841 | 2534 2
842 | 2535 3
843 | 2536 1
844 | 2537 1
845 | 2538 2
846 | 2539 3
847 | 2540 3
848 | 2541 5
849 | 2542 2
850 | 2543 5
851 | 2544 5
852 | 2545 3
853 | 2546 1
854 | 2547 0
855 | 2548 5
856 | 2549 5
857 | 2550 5
858 | 2551 5
859 | 2552 3
860 | 2554 3
861 | 2555 3
862 | 2556 0
863 | 2557 4
864 | 2558 5
865 | 2559 3
866 | 2560 4
867 | 2561 5
868 | 2562 4
869 | 2563 5
870 | 2564 2
871 | 2565 0
872 | 2566 5
873 | 2567 5
874 | 2568 5
875 | 2569 1
876 | 2570 1
877 | 2571 3
878 | 2572 1
879 | 2573 2
880 | 2574 2
881 | 2575 2
882 | 2576 3
883 | 2577 2
884 | 2578 4
885 | 2579 5
886 | 2580 3
887 | 2581 3
888 | 2582 1
889 | 2583 3
890 | 2584 1
891 | 2585 2
892 | 2586 2
893 | 2587 1
894 | 2588 3
895 | 2589 1
896 | 2590 3
897 | 2591 1
898 | 2592 2
899 | 2593 1
900 | 2594 2
901 | 2595 1
902 | 2596 2
903 | 2597 2
904 | 2598 2
905 | 2599 2
906 | 2600 5
907 | 2601 4
908 | 2602 4
909 | 2603 5
910 | 2604 0
911 | 2605 3
912 | 2606 4
913 | 2607 5
914 | 2608 4
915 | 2609 4
916 | 2610 4
917 | 2611 4
918 | 2612 4
919 | 2613 0
920 | 2614 0
921 | 2615 1
922 | 2616 4
923 | 2617 1
924 | 2618 1
925 | 2619 5
926 | 2620 0
927 | 2621 2
928 | 2622 2
929 | 2623 3
930 | 2624 3
931 | 2625 2
932 | 2626 2
933 | 2627 0
934 | 2628 0
935 | 2629 3
936 | 2630 2
937 | 2631 4
938 | 2632 1
939 | 2633 1
940 | 2634 0
941 | 2635 0
942 | 2636 1
943 | 2637 2
944 | 2638 2
945 | 2639 2
946 | 2640 2
947 | 2641 2
948 | 2642 0
949 | 2643 4
950 | 2644 0
951 | 2645 1
952 | 2646 4
953 | 2647 1
954 | 2648 1
955 | 2649 2
956 | 2650 2
957 | 2651 3
958 | 2652 3
959 | 2653 1
960 | 2654 3
961 | 2655 2
962 | 2656 4
963 | 2657 4
964 | 2658 0
965 | 2659 0
966 | 2660 3
967 | 2661 4
968 | 2662 4
969 | 2663 2
970 | 2664 2
971 | 2665 2
972 | 2666 5
973 | 2667 5
974 | 2668 2
975 | 2669 5
976 | 2670 5
977 | 2671 5
978 | 2672 5
979 | 2673 4
980 | 2674 0
981 | 2675 2
982 | 2676 2
983 | 2677 0
984 | 2678 2
985 | 2679 4
986 | 2680 5
987 | 2681 4
988 | 2683 0
989 | 2684 3
990 | 2685 3
991 | 2686 5
992 | 2687 3
993 | 2688 3
994 | 2689 4
995 | 2690 2
996 | 2691 1
997 | 2692 5
998 | 2693 5
999 | 2694 0
1000 | 2695 1
1001 | 2696 3
1002 | 2697 3
1003 | 2698 3
1004 | 2699 5
1005 | 2700 3
1006 | 2701 3
1007 | 2702 1
1008 | 2703 1
1009 | 2704 1
1010 | 2705 1
1011 | 2706 1
1012 | 2707 1
1013 | 2708 1
1014 | 2709 1
1015 | 2710 1
1016 | 2711 1
1017 | 2712 1
1018 | 2713 4
1019 | 2714 2
1020 | 2715 2
1021 | 2716 0
1022 | 2717 2
1023 | 2718 2
1024 | 2719 2
1025 | 2720 2
1026 | 2721 4
1027 | 2722 3
1028 | 2723 3
1029 | 2724 5
1030 | 2725 5
1031 | 2726 4
1032 | 2727 5
1033 | 2728 2
1034 | 2729 4
1035 | 2730 4
1036 | 2731 4
1037 | 2732 5
1038 | 2733 5
1039 | 2734 4
1040 | 2735 2
1041 | 2736 2
1042 | 2737 3
1043 | 2738 3
1044 | 2739 4
1045 | 2740 4
1046 | 2741 3
1047 | 2742 1
1048 | 2743 3
1049 | 2744 2
1050 | 2745 0
1051 | 2746 5
1052 | 2747 5
1053 | 2748 5
1054 | 2749 3
1055 | 2750 4
1056 | 2751 1
1057 | 2752 4
1058 | 2753 0
1059 | 2754 5
1060 | 2755 5
1061 | 2756 0
1062 | 2757 3
1063 | 2758 0
1064 | 2759 2
1065 | 2760 3
1066 | 2761 5
1067 | 2762 3
1068 | 2763 4
1069 | 2764 2
1070 | 2765 2
1071 | 2766 3
1072 | 2767 5
1073 | 2768 1
1074 | 2769 5
1075 | 2770 3
1076 | 2771 4
1077 | 2772 5
1078 | 2773 5
1079 | 2774 2
1080 | 2775 2
1081 | 2776 4
1082 | 2777 3
1083 | 2778 3
1084 | 2779 3
1085 | 2780 3
1086 | 2782 2
1087 | 2783 2
1088 | 2784 2
1089 | 2785 2
1090 | 2786 2
1091 | 2787 3
1092 | 2788 0
1093 | 2789 0
1094 | 2790 5
1095 | 2791 1
1096 | 2792 2
1097 | 2793 3
1098 | 2794 3
1099 | 2795 1
1100 | 2796 3
1101 | 2797 2
1102 | 2798 4
1103 | 2799 3
1104 | 2800 1
1105 | 2801 3
1106 | 2802 3
1107 | 2803 3
1108 | 2804 3
1109 | 2805 3
1110 | 2806 1
1111 | 2807 0
1112 | 2808 5
1113 | 2809 4
1114 | 2810 4
1115 | 2811 1
1116 | 2812 1
1117 | 2813 3
1118 | 2814 4
1119 | 2815 4
1120 | 2816 4
1121 | 2817 4
1122 | 2818 5
1123 | 2819 4
1124 | 2820 2
1125 | 2821 2
1126 | 2822 2
1127 | 2823 2
1128 | 2824 2
1129 | 2825 2
1130 | 2826 2
1131 | 2827 3
1132 | 2828 2
1133 | 2829 2
1134 | 2830 2
1135 | 2831 1
1136 | 2832 4
1137 | 2833 0
1138 | 2834 1
1139 | 2835 4
1140 | 2836 4
1141 | 2837 4
1142 | 2838 1
1143 | 2839 2
1144 | 2840 1
1145 | 2841 5
1146 | 2842 5
1147 | 2843 2
1148 | 2844 4
1149 | 2845 4
1150 | 2846 2
1151 | 2847 2
1152 | 2848 3
1153 | 2849 1
1154 | 2850 1
1155 | 2851 0
1156 | 2852 0
1157 | 2853 2
1158 | 2854 1
1159 | 2855 0
1160 | 2856 1
1161 | 2857 5
1162 | 2858 1
1163 | 2859 2
1164 | 2860 2
1165 | 2861 3
1166 | 2862 2
1167 | 2863 0
1168 | 2864 0
1169 | 2865 3
1170 | 2866 3
1171 | 2867 3
1172 | 2868 2
1173 | 2869 2
1174 | 2870 2
1175 | 2871 1
1176 | 2872 1
1177 | 2873 1
1178 | 2874 3
1179 | 2875 3
1180 | 2876 3
1181 | 2877 5
1182 | 2878 3
1183 | 2879 5
1184 | 2880 2
1185 | 2881 3
1186 | 2882 2
1187 | 2883 3
1188 | 2884 1
1189 | 2885 5
1190 | 2886 2
1191 | 2887 2
1192 | 2888 3
1193 | 2889 3
1194 | 2890 3
1195 | 2891 1
1196 | 2892 1
1197 | 2893 1
1198 | 2894 3
1199 | 2895 3
1200 | 2896 3
1201 | 2897 3
1202 | 2898 4
1203 | 2899 4
1204 | 2900 1
1205 | 2901 4
1206 | 2902 4
1207 | 2903 1
1208 | 2904 3
1209 | 2905 3
1210 | 2906 1
1211 | 2907 0
1212 | 2908 3
1213 | 2909 5
1214 | 2910 4
1215 | 2911 4
1216 | 2912 2
1217 | 2913 4
1218 | 2914 1
1219 | 2915 0
1220 | 2916 3
1221 | 2917 1
1222 | 2918 4
1223 | 2919 1
1224 | 2920 4
1225 | 2921 4
1226 | 2922 0
1227 | 2923 5
1228 | 2924 3
1229 | 2925 2
1230 | 2926 2
1231 | 2927 2
1232 | 2928 5
1233 | 2929 5
1234 | 2930 0
1235 | 2931 4
1236 | 2932 4
1237 | 2933 1
1238 | 2934 2
1239 | 2935 2
1240 | 2936 3
1241 | 2937 3
1242 | 2938 3
1243 | 2939 5
1244 | 2940 5
1245 | 2941 5
1246 | 2942 1
1247 | 2943 5
1248 | 2944 1
1249 | 2945 4
1250 | 2946 3
1251 | 2947 1
1252 | 2948 5
1253 | 2949 5
1254 | 2950 4
1255 | 2951 4
1256 | 2952 2
1257 | 2954 3
1258 | 2955 1
1259 | 2956 0
1260 | 2957 0
1261 | 2958 5
1262 | 2959 3
1263 | 2960 1
1264 | 2961 2
1265 | 2962 1
1266 | 2963 4
1267 | 2964 1
1268 | 2965 4
1269 | 2966 1
1270 | 2967 2
1271 | 2968 2
1272 | 2969 5
1273 | 2970 1
1274 | 2971 2
1275 | 2972 1
1276 | 2973 4
1277 | 2974 5
1278 | 2975 5
1279 | 2976 1
1280 | 2977 4
1281 | 2978 5
1282 | 2979 5
1283 | 2980 1
1284 | 2981 1
1285 | 2982 5
1286 | 2983 5
1287 | 2984 3
1288 | 2985 1
1289 | 2986 0
1290 | 2987 0
1291 | 2988 1
1292 | 2989 0
1293 | 2990 0
1294 | 2991 2
1295 | 2992 0
1296 | 2993 4
1297 | 2994 3
1298 | 2995 4
1299 | 2996 3
1300 | 2997 3
1301 | 2998 1
1302 | 2999 2
1303 | 3000 3
1304 | 3001 5
1305 | 3002 3
1306 | 3003 5
1307 | 3004 5
1308 | 3005 5
1309 | 3006 5
1310 | 3007 5
1311 | 3008 3
1312 | 3009 4
1313 | 3010 4
1314 | 3011 5
1315 | 3012 4
1316 | 3013 2
1317 | 3014 2
1318 | 3015 5
1319 | 3016 1
1320 | 3017 4
1321 | 3018 4
1322 | 3019 4
1323 | 3020 3
1324 | 3021 1
1325 | 3022 5
1326 | 3023 3
1327 | 3024 1
1328 | 3025 3
1329 | 3026 4
1330 | 3027 2
1331 | 3028 2
1332 | 3029 4
1333 | 3030 2
1334 | 3031 1
1335 | 3032 5
1336 | 3033 2
1337 | 3034 2
1338 | 3035 5
1339 | 3036 5
1340 | 3037 3
1341 | 3038 3
1342 | 3039 4
1343 | 3040 1
1344 | 3041 1
1345 | 3043 2
1346 | 3044 5
1347 | 3045 3
1348 | 3046 4
1349 | 3047 4
1350 | 3048 4
1351 | 3049 5
1352 | 3050 5
1353 | 3051 1
1354 | 3052 5
1355 | 3053 5
1356 | 3054 1
1357 | 3055 5
1358 | 3056 5
1359 | 3057 1
1360 | 3058 1
1361 | 3059 1
1362 | 3060 4
1363 | 3061 2
1364 | 3062 3
1365 | 3064 5
1366 | 3065 4
1367 | 3066 1
1368 | 3067 1
1369 | 3068 4
1370 | 3069 5
1371 | 3070 2
1372 | 3071 3
1373 | 3072 1
1374 | 3073 2
1375 | 3074 1
1376 | 3075 4
1377 | 3076 1
1378 | 3077 4
1379 | 3078 1
1380 | 3079 1
1381 | 3080 1
1382 | 3081 0
1383 | 3082 0
1384 | 3083 1
1385 | 3084 5
1386 | 3085 0
1387 | 3086 2
1388 | 3087 1
1389 | 3088 1
1390 | 3089 5
1391 | 3090 1
1392 | 3091 1
1393 | 3092 3
1394 | 3093 2
1395 | 3094 3
1396 | 3095 3
1397 | 3096 1
1398 | 3097 1
1399 | 3098 2
1400 | 3099 3
1401 | 3100 2
1402 | 3101 3
1403 | 3102 5
1404 | 3103 5
1405 | 3104 5
1406 | 3105 5
1407 | 3106 5
1408 | 3107 5
1409 | 3108 5
1410 | 3109 5
1411 | 3110 5
1412 | 3111 3
1413 | 3112 3
1414 | 3113 5
1415 | 3114 2
1416 | 3115 2
1417 | 3116 3
1418 | 3117 4
1419 | 3118 4
1420 | 3119 4
1421 | 3120 4
1422 | 3121 0
1423 | 3122 3
1424 | 3123 0
1425 | 3124 3
1426 | 3125 4
1427 | 3126 1
1428 | 3127 1
1429 | 3128 3
1430 | 3129 3
1431 | 3130 0
1432 | 3131 4
1433 | 3132 5
1434 | 3133 0
1435 | 3134 0
1436 | 3135 0
1437 | 3136 2
1438 | 3137 1
1439 | 3138 3
1440 | 3139 4
1441 | 3140 5
1442 | 3141 2
1443 | 3142 1
1444 | 3143 1
1445 | 3144 3
1446 | 3145 3
1447 | 3146 4
1448 | 3147 4
1449 | 3148 4
1450 | 3149 2
1451 | 3150 2
1452 | 3151 1
1453 | 3152 5
1454 | 3153 4
1455 | 3154 0
1456 | 3155 5
1457 | 3156 5
1458 | 3157 4
1459 | 3158 3
1460 | 3159 4
1461 | 3160 5
1462 | 3161 0
1463 | 3162 3
1464 | 3163 0
1465 | 3164 3
1466 | 3165 4
1467 | 3166 4
1468 | 3167 3
1469 | 3168 3
1470 | 3169 3
1471 | 3170 3
1472 | 3171 3
1473 | 3172 3
1474 | 3173 3
1475 | 3174 5
1476 | 3175 2
1477 | 3176 0
1478 | 3177 0
1479 | 3178 1
1480 | 3179 0
1481 | 3180 0
1482 | 3181 0
1483 | 3182 3
1484 | 3183 1
1485 | 3184 5
1486 | 3185 3
1487 | 3186 2
1488 | 3187 3
1489 | 3188 5
1490 | 3189 3
1491 | 3190 3
1492 | 3191 3
1493 | 3192 1
1494 | 3193 5
1495 | 3194 5
1496 | 3195 5
1497 | 3196 5
1498 | 3197 1
1499 | 3198 2
1500 | 3199 1
1501 | 3200 4
1502 | 3201 5
1503 | 3202 4
1504 | 3203 3
1505 | 3204 3
1506 | 3205 5
1507 | 3206 5
1508 | 3207 1
1509 | 3208 4
1510 | 3209 2
1511 | 3210 5
1512 | 3211 4
1513 | 3213 1
1514 | 3215 4
1515 | 3216 4
1516 | 3217 4
1517 | 3218 4
1518 | 3219 5
1519 | 3220 5
1520 | 3221 4
1521 | 3222 3
1522 | 3223 4
1523 | 3224 3
1524 | 3225 5
1525 | 3226 3
1526 | 3227 3
1527 | 3228 1
1528 | 3229 1
1529 | 3230 0
1530 | 3231 4
1531 | 3232 4
1532 | 3233 3
1533 | 3234 1
1534 | 3235 1
1535 | 3236 1
1536 | 3237 1
1537 | 3238 3
1538 | 3239 3
1539 | 3240 3
1540 | 3241 4
1541 | 3242 3
1542 | 3243 1
1543 | 3244 4
1544 | 3245 1
1545 | 3246 1
1546 | 3247 3
1547 | 3248 5
1548 | 3249 5
1549 | 3251 5
1550 | 3252 4
1551 | 3253 4
1552 | 3254 1
1553 | 3255 3
1554 | 3256 1
1555 | 3257 4
1556 | 3258 3
1557 | 3259 3
1558 | 3260 3
1559 | 3261 1
1560 | 3262 2
1561 | 3263 2
1562 | 3264 5
1563 | 3265 3
1564 | 3266 2
1565 | 3267 5
1566 | 3268 1
1567 | 3269 3
1568 | 3270 3
1569 | 3271 5
1570 | 3272 5
1571 | 3273 4
1572 | 3274 0
1573 | 3275 3
1574 | 3276 5
1575 | 3277 5
1576 | 3278 5
1577 | 3279 1
1578 | 3280 2
1579 | 3281 2
1580 | 3282 4
1581 | 3283 1
1582 | 3284 4
1583 | 3285 5
1584 | 3286 5
1585 | 3287 5
1586 | 3288 4
1587 | 3289 5
1588 | 3290 2
1589 | 3291 1
1590 | 3293 5
1591 | 3294 4
1592 | 3295 4
1593 | 3296 0
1594 | 3297 3
1595 | 3298 5
1596 | 3299 4
1597 | 3300 1
1598 | 3301 3
1599 | 3302 3
1600 | 3303 5
1601 | 3304 4
1602 | 3307 2
1603 | 3308 1
1604 | 3310 0
1605 | 3311 1
1606 | 3312 3
1607 | 3313 2
1608 | 3314 4
1609 | 3315 3
1610 | 3316 2
1611 | 3317 4
1612 | 3318 4
1613 | 3319 1
1614 | 3320 1
1615 | 3321 0
1616 | 3322 3
1617 | 3323 3
1618 | 3324 3
1619 | 3325 1
1620 | 3326 5
1621 |
--------------------------------------------------------------------------------
/semisupervised/data/citeseer/test.txt:
--------------------------------------------------------------------------------
1 | 2312
2 | 2313
3 | 2314
4 | 2315
5 | 2316
6 | 2317
7 | 2318
8 | 2319
9 | 2320
10 | 2321
11 | 2322
12 | 2323
13 | 2324
14 | 2325
15 | 2326
16 | 2327
17 | 2328
18 | 2329
19 | 2330
20 | 2331
21 | 2332
22 | 2333
23 | 2334
24 | 2335
25 | 2336
26 | 2337
27 | 2338
28 | 2339
29 | 2340
30 | 2341
31 | 2342
32 | 2343
33 | 2344
34 | 2345
35 | 2346
36 | 2347
37 | 2348
38 | 2349
39 | 2350
40 | 2351
41 | 2352
42 | 2353
43 | 2354
44 | 2355
45 | 2356
46 | 2357
47 | 2358
48 | 2359
49 | 2360
50 | 2361
51 | 2362
52 | 2363
53 | 2364
54 | 2365
55 | 2366
56 | 2367
57 | 2368
58 | 2369
59 | 2370
60 | 2371
61 | 2372
62 | 2373
63 | 2374
64 | 2375
65 | 2376
66 | 2377
67 | 2378
68 | 2379
69 | 2380
70 | 2381
71 | 2382
72 | 2383
73 | 2384
74 | 2385
75 | 2386
76 | 2387
77 | 2388
78 | 2389
79 | 2390
80 | 2391
81 | 2392
82 | 2393
83 | 2394
84 | 2395
85 | 2396
86 | 2397
87 | 2398
88 | 2399
89 | 2400
90 | 2401
91 | 2402
92 | 2403
93 | 2404
94 | 2405
95 | 2406
96 | 2408
97 | 2409
98 | 2410
99 | 2411
100 | 2412
101 | 2413
102 | 2414
103 | 2415
104 | 2416
105 | 2417
106 | 2418
107 | 2419
108 | 2420
109 | 2421
110 | 2422
111 | 2423
112 | 2424
113 | 2425
114 | 2426
115 | 2427
116 | 2428
117 | 2429
118 | 2430
119 | 2431
120 | 2432
121 | 2433
122 | 2434
123 | 2435
124 | 2436
125 | 2437
126 | 2438
127 | 2439
128 | 2440
129 | 2441
130 | 2442
131 | 2443
132 | 2444
133 | 2445
134 | 2446
135 | 2447
136 | 2448
137 | 2449
138 | 2450
139 | 2451
140 | 2452
141 | 2453
142 | 2454
143 | 2455
144 | 2456
145 | 2457
146 | 2458
147 | 2459
148 | 2460
149 | 2461
150 | 2462
151 | 2463
152 | 2464
153 | 2465
154 | 2466
155 | 2467
156 | 2468
157 | 2469
158 | 2470
159 | 2471
160 | 2472
161 | 2473
162 | 2474
163 | 2475
164 | 2476
165 | 2477
166 | 2478
167 | 2479
168 | 2480
169 | 2481
170 | 2482
171 | 2483
172 | 2484
173 | 2485
174 | 2486
175 | 2487
176 | 2488
177 | 2490
178 | 2491
179 | 2492
180 | 2493
181 | 2494
182 | 2495
183 | 2496
184 | 2497
185 | 2498
186 | 2499
187 | 2500
188 | 2501
189 | 2502
190 | 2503
191 | 2504
192 | 2505
193 | 2506
194 | 2507
195 | 2508
196 | 2509
197 | 2510
198 | 2511
199 | 2512
200 | 2513
201 | 2514
202 | 2515
203 | 2516
204 | 2517
205 | 2518
206 | 2519
207 | 2520
208 | 2521
209 | 2522
210 | 2523
211 | 2524
212 | 2525
213 | 2526
214 | 2527
215 | 2528
216 | 2529
217 | 2530
218 | 2531
219 | 2532
220 | 2533
221 | 2534
222 | 2535
223 | 2536
224 | 2537
225 | 2538
226 | 2539
227 | 2540
228 | 2541
229 | 2542
230 | 2543
231 | 2544
232 | 2545
233 | 2546
234 | 2547
235 | 2548
236 | 2549
237 | 2550
238 | 2551
239 | 2552
240 | 2554
241 | 2555
242 | 2556
243 | 2557
244 | 2558
245 | 2559
246 | 2560
247 | 2561
248 | 2562
249 | 2563
250 | 2564
251 | 2565
252 | 2566
253 | 2567
254 | 2568
255 | 2569
256 | 2570
257 | 2571
258 | 2572
259 | 2573
260 | 2574
261 | 2575
262 | 2576
263 | 2577
264 | 2578
265 | 2579
266 | 2580
267 | 2581
268 | 2582
269 | 2583
270 | 2584
271 | 2585
272 | 2586
273 | 2587
274 | 2588
275 | 2589
276 | 2590
277 | 2591
278 | 2592
279 | 2593
280 | 2594
281 | 2595
282 | 2596
283 | 2597
284 | 2598
285 | 2599
286 | 2600
287 | 2601
288 | 2602
289 | 2603
290 | 2604
291 | 2605
292 | 2606
293 | 2607
294 | 2608
295 | 2609
296 | 2610
297 | 2611
298 | 2612
299 | 2613
300 | 2614
301 | 2615
302 | 2616
303 | 2617
304 | 2618
305 | 2619
306 | 2620
307 | 2621
308 | 2622
309 | 2623
310 | 2624
311 | 2625
312 | 2626
313 | 2627
314 | 2628
315 | 2629
316 | 2630
317 | 2631
318 | 2632
319 | 2633
320 | 2634
321 | 2635
322 | 2636
323 | 2637
324 | 2638
325 | 2639
326 | 2640
327 | 2641
328 | 2642
329 | 2643
330 | 2644
331 | 2645
332 | 2646
333 | 2647
334 | 2648
335 | 2649
336 | 2650
337 | 2651
338 | 2652
339 | 2653
340 | 2654
341 | 2655
342 | 2656
343 | 2657
344 | 2658
345 | 2659
346 | 2660
347 | 2661
348 | 2662
349 | 2663
350 | 2664
351 | 2665
352 | 2666
353 | 2667
354 | 2668
355 | 2669
356 | 2670
357 | 2671
358 | 2672
359 | 2673
360 | 2674
361 | 2675
362 | 2676
363 | 2677
364 | 2678
365 | 2679
366 | 2680
367 | 2681
368 | 2683
369 | 2684
370 | 2685
371 | 2686
372 | 2687
373 | 2688
374 | 2689
375 | 2690
376 | 2691
377 | 2692
378 | 2693
379 | 2694
380 | 2695
381 | 2696
382 | 2697
383 | 2698
384 | 2699
385 | 2700
386 | 2701
387 | 2702
388 | 2703
389 | 2704
390 | 2705
391 | 2706
392 | 2707
393 | 2708
394 | 2709
395 | 2710
396 | 2711
397 | 2712
398 | 2713
399 | 2714
400 | 2715
401 | 2716
402 | 2717
403 | 2718
404 | 2719
405 | 2720
406 | 2721
407 | 2722
408 | 2723
409 | 2724
410 | 2725
411 | 2726
412 | 2727
413 | 2728
414 | 2729
415 | 2730
416 | 2731
417 | 2732
418 | 2733
419 | 2734
420 | 2735
421 | 2736
422 | 2737
423 | 2738
424 | 2739
425 | 2740
426 | 2741
427 | 2742
428 | 2743
429 | 2744
430 | 2745
431 | 2746
432 | 2747
433 | 2748
434 | 2749
435 | 2750
436 | 2751
437 | 2752
438 | 2753
439 | 2754
440 | 2755
441 | 2756
442 | 2757
443 | 2758
444 | 2759
445 | 2760
446 | 2761
447 | 2762
448 | 2763
449 | 2764
450 | 2765
451 | 2766
452 | 2767
453 | 2768
454 | 2769
455 | 2770
456 | 2771
457 | 2772
458 | 2773
459 | 2774
460 | 2775
461 | 2776
462 | 2777
463 | 2778
464 | 2779
465 | 2780
466 | 2782
467 | 2783
468 | 2784
469 | 2785
470 | 2786
471 | 2787
472 | 2788
473 | 2789
474 | 2790
475 | 2791
476 | 2792
477 | 2793
478 | 2794
479 | 2795
480 | 2796
481 | 2797
482 | 2798
483 | 2799
484 | 2800
485 | 2801
486 | 2802
487 | 2803
488 | 2804
489 | 2805
490 | 2806
491 | 2807
492 | 2808
493 | 2809
494 | 2810
495 | 2811
496 | 2812
497 | 2813
498 | 2814
499 | 2815
500 | 2816
501 | 2817
502 | 2818
503 | 2819
504 | 2820
505 | 2821
506 | 2822
507 | 2823
508 | 2824
509 | 2825
510 | 2826
511 | 2827
512 | 2828
513 | 2829
514 | 2830
515 | 2831
516 | 2832
517 | 2833
518 | 2834
519 | 2835
520 | 2836
521 | 2837
522 | 2838
523 | 2839
524 | 2840
525 | 2841
526 | 2842
527 | 2843
528 | 2844
529 | 2845
530 | 2846
531 | 2847
532 | 2848
533 | 2849
534 | 2850
535 | 2851
536 | 2852
537 | 2853
538 | 2854
539 | 2855
540 | 2856
541 | 2857
542 | 2858
543 | 2859
544 | 2860
545 | 2861
546 | 2862
547 | 2863
548 | 2864
549 | 2865
550 | 2866
551 | 2867
552 | 2868
553 | 2869
554 | 2870
555 | 2871
556 | 2872
557 | 2873
558 | 2874
559 | 2875
560 | 2876
561 | 2877
562 | 2878
563 | 2879
564 | 2880
565 | 2881
566 | 2882
567 | 2883
568 | 2884
569 | 2885
570 | 2886
571 | 2887
572 | 2888
573 | 2889
574 | 2890
575 | 2891
576 | 2892
577 | 2893
578 | 2894
579 | 2895
580 | 2896
581 | 2897
582 | 2898
583 | 2899
584 | 2900
585 | 2901
586 | 2902
587 | 2903
588 | 2904
589 | 2905
590 | 2906
591 | 2907
592 | 2908
593 | 2909
594 | 2910
595 | 2911
596 | 2912
597 | 2913
598 | 2914
599 | 2915
600 | 2916
601 | 2917
602 | 2918
603 | 2919
604 | 2920
605 | 2921
606 | 2922
607 | 2923
608 | 2924
609 | 2925
610 | 2926
611 | 2927
612 | 2928
613 | 2929
614 | 2930
615 | 2931
616 | 2932
617 | 2933
618 | 2934
619 | 2935
620 | 2936
621 | 2937
622 | 2938
623 | 2939
624 | 2940
625 | 2941
626 | 2942
627 | 2943
628 | 2944
629 | 2945
630 | 2946
631 | 2947
632 | 2948
633 | 2949
634 | 2950
635 | 2951
636 | 2952
637 | 2954
638 | 2955
639 | 2956
640 | 2957
641 | 2958
642 | 2959
643 | 2960
644 | 2961
645 | 2962
646 | 2963
647 | 2964
648 | 2965
649 | 2966
650 | 2967
651 | 2968
652 | 2969
653 | 2970
654 | 2971
655 | 2972
656 | 2973
657 | 2974
658 | 2975
659 | 2976
660 | 2977
661 | 2978
662 | 2979
663 | 2980
664 | 2981
665 | 2982
666 | 2983
667 | 2984
668 | 2985
669 | 2986
670 | 2987
671 | 2988
672 | 2989
673 | 2990
674 | 2991
675 | 2992
676 | 2993
677 | 2994
678 | 2995
679 | 2996
680 | 2997
681 | 2998
682 | 2999
683 | 3000
684 | 3001
685 | 3002
686 | 3003
687 | 3004
688 | 3005
689 | 3006
690 | 3007
691 | 3008
692 | 3009
693 | 3010
694 | 3011
695 | 3012
696 | 3013
697 | 3014
698 | 3015
699 | 3016
700 | 3017
701 | 3018
702 | 3019
703 | 3020
704 | 3021
705 | 3022
706 | 3023
707 | 3024
708 | 3025
709 | 3026
710 | 3027
711 | 3028
712 | 3029
713 | 3030
714 | 3031
715 | 3032
716 | 3033
717 | 3034
718 | 3035
719 | 3036
720 | 3037
721 | 3038
722 | 3039
723 | 3040
724 | 3041
725 | 3043
726 | 3044
727 | 3045
728 | 3046
729 | 3047
730 | 3048
731 | 3049
732 | 3050
733 | 3051
734 | 3052
735 | 3053
736 | 3054
737 | 3055
738 | 3056
739 | 3057
740 | 3058
741 | 3059
742 | 3060
743 | 3061
744 | 3062
745 | 3064
746 | 3065
747 | 3066
748 | 3067
749 | 3068
750 | 3069
751 | 3070
752 | 3071
753 | 3072
754 | 3073
755 | 3074
756 | 3075
757 | 3076
758 | 3077
759 | 3078
760 | 3079
761 | 3080
762 | 3081
763 | 3082
764 | 3083
765 | 3084
766 | 3085
767 | 3086
768 | 3087
769 | 3088
770 | 3089
771 | 3090
772 | 3091
773 | 3092
774 | 3093
775 | 3094
776 | 3095
777 | 3096
778 | 3097
779 | 3098
780 | 3099
781 | 3100
782 | 3101
783 | 3102
784 | 3103
785 | 3104
786 | 3105
787 | 3106
788 | 3107
789 | 3108
790 | 3109
791 | 3110
792 | 3111
793 | 3112
794 | 3113
795 | 3114
796 | 3115
797 | 3116
798 | 3117
799 | 3118
800 | 3119
801 | 3120
802 | 3121
803 | 3122
804 | 3123
805 | 3124
806 | 3125
807 | 3126
808 | 3127
809 | 3128
810 | 3129
811 | 3130
812 | 3131
813 | 3132
814 | 3133
815 | 3134
816 | 3135
817 | 3136
818 | 3137
819 | 3138
820 | 3139
821 | 3140
822 | 3141
823 | 3142
824 | 3143
825 | 3144
826 | 3145
827 | 3146
828 | 3147
829 | 3148
830 | 3149
831 | 3150
832 | 3151
833 | 3152
834 | 3153
835 | 3154
836 | 3155
837 | 3156
838 | 3157
839 | 3158
840 | 3159
841 | 3160
842 | 3161
843 | 3162
844 | 3163
845 | 3164
846 | 3165
847 | 3166
848 | 3167
849 | 3168
850 | 3169
851 | 3170
852 | 3171
853 | 3172
854 | 3173
855 | 3174
856 | 3175
857 | 3176
858 | 3177
859 | 3178
860 | 3179
861 | 3180
862 | 3181
863 | 3182
864 | 3183
865 | 3184
866 | 3185
867 | 3186
868 | 3187
869 | 3188
870 | 3189
871 | 3190
872 | 3191
873 | 3192
874 | 3193
875 | 3194
876 | 3195
877 | 3196
878 | 3197
879 | 3198
880 | 3199
881 | 3200
882 | 3201
883 | 3202
884 | 3203
885 | 3204
886 | 3205
887 | 3206
888 | 3207
889 | 3208
890 | 3209
891 | 3210
892 | 3211
893 | 3213
894 | 3215
895 | 3216
896 | 3217
897 | 3218
898 | 3219
899 | 3220
900 | 3221
901 | 3222
902 | 3223
903 | 3224
904 | 3225
905 | 3226
906 | 3227
907 | 3228
908 | 3229
909 | 3230
910 | 3231
911 | 3232
912 | 3233
913 | 3234
914 | 3235
915 | 3236
916 | 3237
917 | 3238
918 | 3239
919 | 3240
920 | 3241
921 | 3242
922 | 3243
923 | 3244
924 | 3245
925 | 3246
926 | 3247
927 | 3248
928 | 3249
929 | 3251
930 | 3252
931 | 3253
932 | 3254
933 | 3255
934 | 3256
935 | 3257
936 | 3258
937 | 3259
938 | 3260
939 | 3261
940 | 3262
941 | 3263
942 | 3264
943 | 3265
944 | 3266
945 | 3267
946 | 3268
947 | 3269
948 | 3270
949 | 3271
950 | 3272
951 | 3273
952 | 3274
953 | 3275
954 | 3276
955 | 3277
956 | 3278
957 | 3279
958 | 3280
959 | 3281
960 | 3282
961 | 3283
962 | 3284
963 | 3285
964 | 3286
965 | 3287
966 | 3288
967 | 3289
968 | 3290
969 | 3291
970 | 3293
971 | 3294
972 | 3295
973 | 3296
974 | 3297
975 | 3298
976 | 3299
977 | 3300
978 | 3301
979 | 3302
980 | 3303
981 | 3304
982 | 3307
983 | 3308
984 | 3310
985 | 3311
986 | 3312
987 | 3313
988 | 3314
989 | 3315
990 | 3316
991 | 3317
992 | 3318
993 | 3319
994 | 3320
995 | 3321
996 | 3322
997 | 3323
998 | 3324
999 | 3325
1000 | 3326
1001 |
--------------------------------------------------------------------------------
/semisupervised/data/citeseer/train.txt:
--------------------------------------------------------------------------------
1 | 0
2 | 1
3 | 2
4 | 3
5 | 4
6 | 5
7 | 6
8 | 7
9 | 8
10 | 9
11 | 10
12 | 11
13 | 12
14 | 13
15 | 14
16 | 15
17 | 16
18 | 17
19 | 18
20 | 19
21 | 20
22 | 21
23 | 22
24 | 23
25 | 24
26 | 25
27 | 26
28 | 27
29 | 28
30 | 29
31 | 30
32 | 31
33 | 32
34 | 33
35 | 34
36 | 35
37 | 36
38 | 37
39 | 38
40 | 39
41 | 40
42 | 41
43 | 42
44 | 43
45 | 44
46 | 45
47 | 46
48 | 47
49 | 48
50 | 49
51 | 50
52 | 51
53 | 52
54 | 53
55 | 54
56 | 55
57 | 56
58 | 57
59 | 58
60 | 59
61 | 60
62 | 61
63 | 62
64 | 63
65 | 64
66 | 65
67 | 66
68 | 67
69 | 68
70 | 69
71 | 70
72 | 71
73 | 72
74 | 73
75 | 74
76 | 75
77 | 76
78 | 77
79 | 78
80 | 79
81 | 80
82 | 81
83 | 82
84 | 83
85 | 84
86 | 85
87 | 86
88 | 87
89 | 88
90 | 89
91 | 90
92 | 91
93 | 92
94 | 93
95 | 94
96 | 95
97 | 96
98 | 97
99 | 98
100 | 99
101 | 100
102 | 101
103 | 102
104 | 103
105 | 104
106 | 105
107 | 106
108 | 107
109 | 108
110 | 109
111 | 110
112 | 111
113 | 112
114 | 113
115 | 114
116 | 115
117 | 116
118 | 117
119 | 118
120 | 119
121 |
--------------------------------------------------------------------------------
/semisupervised/data/cora/dev.txt:
--------------------------------------------------------------------------------
1 | 140
2 | 141
3 | 142
4 | 143
5 | 144
6 | 145
7 | 146
8 | 147
9 | 148
10 | 149
11 | 150
12 | 151
13 | 152
14 | 153
15 | 154
16 | 155
17 | 156
18 | 157
19 | 158
20 | 159
21 | 160
22 | 161
23 | 162
24 | 163
25 | 164
26 | 165
27 | 166
28 | 167
29 | 168
30 | 169
31 | 170
32 | 171
33 | 172
34 | 173
35 | 174
36 | 175
37 | 176
38 | 177
39 | 178
40 | 179
41 | 180
42 | 181
43 | 182
44 | 183
45 | 184
46 | 185
47 | 186
48 | 187
49 | 188
50 | 189
51 | 190
52 | 191
53 | 192
54 | 193
55 | 194
56 | 195
57 | 196
58 | 197
59 | 198
60 | 199
61 | 200
62 | 201
63 | 202
64 | 203
65 | 204
66 | 205
67 | 206
68 | 207
69 | 208
70 | 209
71 | 210
72 | 211
73 | 212
74 | 213
75 | 214
76 | 215
77 | 216
78 | 217
79 | 218
80 | 219
81 | 220
82 | 221
83 | 222
84 | 223
85 | 224
86 | 225
87 | 226
88 | 227
89 | 228
90 | 229
91 | 230
92 | 231
93 | 232
94 | 233
95 | 234
96 | 235
97 | 236
98 | 237
99 | 238
100 | 239
101 | 240
102 | 241
103 | 242
104 | 243
105 | 244
106 | 245
107 | 246
108 | 247
109 | 248
110 | 249
111 | 250
112 | 251
113 | 252
114 | 253
115 | 254
116 | 255
117 | 256
118 | 257
119 | 258
120 | 259
121 | 260
122 | 261
123 | 262
124 | 263
125 | 264
126 | 265
127 | 266
128 | 267
129 | 268
130 | 269
131 | 270
132 | 271
133 | 272
134 | 273
135 | 274
136 | 275
137 | 276
138 | 277
139 | 278
140 | 279
141 | 280
142 | 281
143 | 282
144 | 283
145 | 284
146 | 285
147 | 286
148 | 287
149 | 288
150 | 289
151 | 290
152 | 291
153 | 292
154 | 293
155 | 294
156 | 295
157 | 296
158 | 297
159 | 298
160 | 299
161 | 300
162 | 301
163 | 302
164 | 303
165 | 304
166 | 305
167 | 306
168 | 307
169 | 308
170 | 309
171 | 310
172 | 311
173 | 312
174 | 313
175 | 314
176 | 315
177 | 316
178 | 317
179 | 318
180 | 319
181 | 320
182 | 321
183 | 322
184 | 323
185 | 324
186 | 325
187 | 326
188 | 327
189 | 328
190 | 329
191 | 330
192 | 331
193 | 332
194 | 333
195 | 334
196 | 335
197 | 336
198 | 337
199 | 338
200 | 339
201 | 340
202 | 341
203 | 342
204 | 343
205 | 344
206 | 345
207 | 346
208 | 347
209 | 348
210 | 349
211 | 350
212 | 351
213 | 352
214 | 353
215 | 354
216 | 355
217 | 356
218 | 357
219 | 358
220 | 359
221 | 360
222 | 361
223 | 362
224 | 363
225 | 364
226 | 365
227 | 366
228 | 367
229 | 368
230 | 369
231 | 370
232 | 371
233 | 372
234 | 373
235 | 374
236 | 375
237 | 376
238 | 377
239 | 378
240 | 379
241 | 380
242 | 381
243 | 382
244 | 383
245 | 384
246 | 385
247 | 386
248 | 387
249 | 388
250 | 389
251 | 390
252 | 391
253 | 392
254 | 393
255 | 394
256 | 395
257 | 396
258 | 397
259 | 398
260 | 399
261 | 400
262 | 401
263 | 402
264 | 403
265 | 404
266 | 405
267 | 406
268 | 407
269 | 408
270 | 409
271 | 410
272 | 411
273 | 412
274 | 413
275 | 414
276 | 415
277 | 416
278 | 417
279 | 418
280 | 419
281 | 420
282 | 421
283 | 422
284 | 423
285 | 424
286 | 425
287 | 426
288 | 427
289 | 428
290 | 429
291 | 430
292 | 431
293 | 432
294 | 433
295 | 434
296 | 435
297 | 436
298 | 437
299 | 438
300 | 439
301 | 440
302 | 441
303 | 442
304 | 443
305 | 444
306 | 445
307 | 446
308 | 447
309 | 448
310 | 449
311 | 450
312 | 451
313 | 452
314 | 453
315 | 454
316 | 455
317 | 456
318 | 457
319 | 458
320 | 459
321 | 460
322 | 461
323 | 462
324 | 463
325 | 464
326 | 465
327 | 466
328 | 467
329 | 468
330 | 469
331 | 470
332 | 471
333 | 472
334 | 473
335 | 474
336 | 475
337 | 476
338 | 477
339 | 478
340 | 479
341 | 480
342 | 481
343 | 482
344 | 483
345 | 484
346 | 485
347 | 486
348 | 487
349 | 488
350 | 489
351 | 490
352 | 491
353 | 492
354 | 493
355 | 494
356 | 495
357 | 496
358 | 497
359 | 498
360 | 499
361 | 500
362 | 501
363 | 502
364 | 503
365 | 504
366 | 505
367 | 506
368 | 507
369 | 508
370 | 509
371 | 510
372 | 511
373 | 512
374 | 513
375 | 514
376 | 515
377 | 516
378 | 517
379 | 518
380 | 519
381 | 520
382 | 521
383 | 522
384 | 523
385 | 524
386 | 525
387 | 526
388 | 527
389 | 528
390 | 529
391 | 530
392 | 531
393 | 532
394 | 533
395 | 534
396 | 535
397 | 536
398 | 537
399 | 538
400 | 539
401 | 540
402 | 541
403 | 542
404 | 543
405 | 544
406 | 545
407 | 546
408 | 547
409 | 548
410 | 549
411 | 550
412 | 551
413 | 552
414 | 553
415 | 554
416 | 555
417 | 556
418 | 557
419 | 558
420 | 559
421 | 560
422 | 561
423 | 562
424 | 563
425 | 564
426 | 565
427 | 566
428 | 567
429 | 568
430 | 569
431 | 570
432 | 571
433 | 572
434 | 573
435 | 574
436 | 575
437 | 576
438 | 577
439 | 578
440 | 579
441 | 580
442 | 581
443 | 582
444 | 583
445 | 584
446 | 585
447 | 586
448 | 587
449 | 588
450 | 589
451 | 590
452 | 591
453 | 592
454 | 593
455 | 594
456 | 595
457 | 596
458 | 597
459 | 598
460 | 599
461 | 600
462 | 601
463 | 602
464 | 603
465 | 604
466 | 605
467 | 606
468 | 607
469 | 608
470 | 609
471 | 610
472 | 611
473 | 612
474 | 613
475 | 614
476 | 615
477 | 616
478 | 617
479 | 618
480 | 619
481 | 620
482 | 621
483 | 622
484 | 623
485 | 624
486 | 625
487 | 626
488 | 627
489 | 628
490 | 629
491 | 630
492 | 631
493 | 632
494 | 633
495 | 634
496 | 635
497 | 636
498 | 637
499 | 638
500 | 639
501 |
--------------------------------------------------------------------------------
/semisupervised/data/cora/label.txt:
--------------------------------------------------------------------------------
1 | 0 3
2 | 1 4
3 | 2 4
4 | 3 0
5 | 4 3
6 | 5 2
7 | 6 0
8 | 7 3
9 | 8 3
10 | 9 2
11 | 10 0
12 | 11 0
13 | 12 4
14 | 13 3
15 | 14 3
16 | 15 3
17 | 16 2
18 | 17 3
19 | 18 1
20 | 19 3
21 | 20 5
22 | 21 3
23 | 22 4
24 | 23 6
25 | 24 3
26 | 25 3
27 | 26 6
28 | 27 3
29 | 28 2
30 | 29 4
31 | 30 3
32 | 31 6
33 | 32 0
34 | 33 4
35 | 34 2
36 | 35 0
37 | 36 1
38 | 37 5
39 | 38 4
40 | 39 4
41 | 40 3
42 | 41 6
43 | 42 6
44 | 43 4
45 | 44 3
46 | 45 3
47 | 46 2
48 | 47 5
49 | 48 3
50 | 49 4
51 | 50 5
52 | 51 3
53 | 52 0
54 | 53 2
55 | 54 1
56 | 55 4
57 | 56 6
58 | 57 3
59 | 58 2
60 | 59 2
61 | 60 0
62 | 61 0
63 | 62 0
64 | 63 4
65 | 64 2
66 | 65 0
67 | 66 4
68 | 67 5
69 | 68 2
70 | 69 6
71 | 70 5
72 | 71 2
73 | 72 2
74 | 73 2
75 | 74 0
76 | 75 4
77 | 76 5
78 | 77 6
79 | 78 4
80 | 79 0
81 | 80 0
82 | 81 0
83 | 82 4
84 | 83 2
85 | 84 4
86 | 85 1
87 | 86 4
88 | 87 6
89 | 88 0
90 | 89 4
91 | 90 2
92 | 91 4
93 | 92 6
94 | 93 6
95 | 94 0
96 | 95 0
97 | 96 6
98 | 97 5
99 | 98 0
100 | 99 6
101 | 100 0
102 | 101 2
103 | 102 1
104 | 103 1
105 | 104 1
106 | 105 2
107 | 106 6
108 | 107 5
109 | 108 6
110 | 109 1
111 | 110 2
112 | 111 2
113 | 112 1
114 | 113 5
115 | 114 5
116 | 115 5
117 | 116 6
118 | 117 5
119 | 118 6
120 | 119 5
121 | 120 5
122 | 121 1
123 | 122 6
124 | 123 6
125 | 124 1
126 | 125 5
127 | 126 1
128 | 127 6
129 | 128 5
130 | 129 5
131 | 130 5
132 | 131 1
133 | 132 5
134 | 133 1
135 | 134 1
136 | 135 1
137 | 136 1
138 | 137 1
139 | 138 1
140 | 139 1
141 | 140 4
142 | 141 3
143 | 142 0
144 | 143 3
145 | 144 6
146 | 145 6
147 | 146 0
148 | 147 3
149 | 148 4
150 | 149 0
151 | 150 3
152 | 151 4
153 | 152 4
154 | 153 1
155 | 154 2
156 | 155 2
157 | 156 2
158 | 157 3
159 | 158 3
160 | 159 3
161 | 160 3
162 | 161 0
163 | 162 4
164 | 163 5
165 | 164 0
166 | 165 3
167 | 166 4
168 | 167 3
169 | 168 3
170 | 169 3
171 | 170 2
172 | 171 3
173 | 172 3
174 | 173 2
175 | 174 2
176 | 175 6
177 | 176 1
178 | 177 4
179 | 178 3
180 | 179 3
181 | 180 3
182 | 181 6
183 | 182 3
184 | 183 3
185 | 184 3
186 | 185 3
187 | 186 0
188 | 187 4
189 | 188 2
190 | 189 2
191 | 190 6
192 | 191 5
193 | 192 3
194 | 193 5
195 | 194 4
196 | 195 0
197 | 196 4
198 | 197 3
199 | 198 4
200 | 199 4
201 | 200 3
202 | 201 3
203 | 202 2
204 | 203 4
205 | 204 0
206 | 205 3
207 | 206 2
208 | 207 3
209 | 208 3
210 | 209 4
211 | 210 4
212 | 211 0
213 | 212 3
214 | 213 6
215 | 214 0
216 | 215 3
217 | 216 3
218 | 217 4
219 | 218 3
220 | 219 3
221 | 220 5
222 | 221 2
223 | 222 3
224 | 223 2
225 | 224 4
226 | 225 1
227 | 226 3
228 | 227 2
229 | 228 2
230 | 229 3
231 | 230 3
232 | 231 3
233 | 232 3
234 | 233 5
235 | 234 1
236 | 235 3
237 | 236 1
238 | 237 3
239 | 238 5
240 | 239 0
241 | 240 3
242 | 241 5
243 | 242 0
244 | 243 4
245 | 244 2
246 | 245 4
247 | 246 2
248 | 247 4
249 | 248 4
250 | 249 5
251 | 250 4
252 | 251 3
253 | 252 5
254 | 253 3
255 | 254 3
256 | 255 4
257 | 256 3
258 | 257 0
259 | 258 4
260 | 259 5
261 | 260 0
262 | 261 3
263 | 262 6
264 | 263 2
265 | 264 5
266 | 265 5
267 | 266 5
268 | 267 3
269 | 268 2
270 | 269 3
271 | 270 0
272 | 271 4
273 | 272 5
274 | 273 3
275 | 274 0
276 | 275 4
277 | 276 0
278 | 277 3
279 | 278 3
280 | 279 0
281 | 280 0
282 | 281 3
283 | 282 5
284 | 283 4
285 | 284 4
286 | 285 3
287 | 286 4
288 | 287 3
289 | 288 3
290 | 289 2
291 | 290 2
292 | 291 3
293 | 292 0
294 | 293 3
295 | 294 1
296 | 295 3
297 | 296 2
298 | 297 3
299 | 298 3
300 | 299 4
301 | 300 5
302 | 301 2
303 | 302 1
304 | 303 1
305 | 304 0
306 | 305 0
307 | 306 1
308 | 307 6
309 | 308 1
310 | 309 3
311 | 310 3
312 | 311 3
313 | 312 2
314 | 313 3
315 | 314 3
316 | 315 0
317 | 316 3
318 | 317 4
319 | 318 1
320 | 319 3
321 | 320 4
322 | 321 3
323 | 322 2
324 | 323 0
325 | 324 0
326 | 325 4
327 | 326 2
328 | 327 3
329 | 328 2
330 | 329 1
331 | 330 4
332 | 331 6
333 | 332 3
334 | 333 2
335 | 334 0
336 | 335 3
337 | 336 3
338 | 337 2
339 | 338 3
340 | 339 4
341 | 340 4
342 | 341 2
343 | 342 1
344 | 343 3
345 | 344 5
346 | 345 3
347 | 346 2
348 | 347 0
349 | 348 4
350 | 349 5
351 | 350 1
352 | 351 3
353 | 352 3
354 | 353 2
355 | 354 0
356 | 355 2
357 | 356 4
358 | 357 2
359 | 358 2
360 | 359 2
361 | 360 5
362 | 361 4
363 | 362 4
364 | 363 2
365 | 364 2
366 | 365 0
367 | 366 3
368 | 367 2
369 | 368 4
370 | 369 4
371 | 370 5
372 | 371 5
373 | 372 1
374 | 373 0
375 | 374 3
376 | 375 4
377 | 376 5
378 | 377 3
379 | 378 4
380 | 379 5
381 | 380 3
382 | 381 4
383 | 382 3
384 | 383 3
385 | 384 1
386 | 385 4
387 | 386 3
388 | 387 3
389 | 388 5
390 | 389 2
391 | 390 3
392 | 391 2
393 | 392 5
394 | 393 5
395 | 394 4
396 | 395 3
397 | 396 3
398 | 397 3
399 | 398 3
400 | 399 1
401 | 400 5
402 | 401 3
403 | 402 3
404 | 403 2
405 | 404 6
406 | 405 0
407 | 406 1
408 | 407 3
409 | 408 0
410 | 409 1
411 | 410 5
412 | 411 3
413 | 412 6
414 | 413 3
415 | 414 6
416 | 415 0
417 | 416 3
418 | 417 3
419 | 418 3
420 | 419 5
421 | 420 4
422 | 421 3
423 | 422 4
424 | 423 0
425 | 424 5
426 | 425 2
427 | 426 1
428 | 427 2
429 | 428 4
430 | 429 4
431 | 430 4
432 | 431 4
433 | 432 3
434 | 433 3
435 | 434 0
436 | 435 4
437 | 436 3
438 | 437 0
439 | 438 5
440 | 439 2
441 | 440 0
442 | 441 5
443 | 442 4
444 | 443 4
445 | 444 4
446 | 445 3
447 | 446 0
448 | 447 6
449 | 448 5
450 | 449 2
451 | 450 4
452 | 451 5
453 | 452 1
454 | 453 3
455 | 454 5
456 | 455 3
457 | 456 0
458 | 457 3
459 | 458 5
460 | 459 1
461 | 460 1
462 | 461 0
463 | 462 3
464 | 463 4
465 | 464 2
466 | 465 6
467 | 466 2
468 | 467 0
469 | 468 5
470 | 469 3
471 | 470 4
472 | 471 6
473 | 472 5
474 | 473 3
475 | 474 5
476 | 475 0
477 | 476 1
478 | 477 3
479 | 478 0
480 | 479 5
481 | 480 2
482 | 481 2
483 | 482 3
484 | 483 5
485 | 484 1
486 | 485 0
487 | 486 3
488 | 487 1
489 | 488 4
490 | 489 2
491 | 490 5
492 | 491 6
493 | 492 4
494 | 493 2
495 | 494 2
496 | 495 6
497 | 496 0
498 | 497 0
499 | 498 4
500 | 499 6
501 | 500 3
502 | 501 2
503 | 502 0
504 | 503 3
505 | 504 6
506 | 505 1
507 | 506 6
508 | 507 3
509 | 508 1
510 | 509 3
511 | 510 3
512 | 511 3
513 | 512 3
514 | 513 2
515 | 514 5
516 | 515 4
517 | 516 5
518 | 517 5
519 | 518 3
520 | 519 1
521 | 520 3
522 | 521 3
523 | 522 4
524 | 523 4
525 | 524 2
526 | 525 0
527 | 526 2
528 | 527 0
529 | 528 5
530 | 529 4
531 | 530 0
532 | 531 0
533 | 532 3
534 | 533 2
535 | 534 2
536 | 535 2
537 | 536 2
538 | 537 6
539 | 538 4
540 | 539 6
541 | 540 5
542 | 541 5
543 | 542 1
544 | 543 0
545 | 544 0
546 | 545 4
547 | 546 3
548 | 547 3
549 | 548 1
550 | 549 3
551 | 550 6
552 | 551 6
553 | 552 2
554 | 553 3
555 | 554 3
556 | 555 3
557 | 556 1
558 | 557 2
559 | 558 2
560 | 559 5
561 | 560 4
562 | 561 3
563 | 562 2
564 | 563 1
565 | 564 2
566 | 565 2
567 | 566 3
568 | 567 2
569 | 568 3
570 | 569 2
571 | 570 3
572 | 571 3
573 | 572 0
574 | 573 5
575 | 574 3
576 | 575 3
577 | 576 3
578 | 577 4
579 | 578 5
580 | 579 3
581 | 580 2
582 | 581 1
583 | 582 4
584 | 583 4
585 | 584 4
586 | 585 4
587 | 586 0
588 | 587 5
589 | 588 4
590 | 589 1
591 | 590 3
592 | 591 0
593 | 592 3
594 | 593 4
595 | 594 6
596 | 595 3
597 | 596 6
598 | 597 3
599 | 598 3
600 | 599 3
601 | 600 6
602 | 601 3
603 | 602 4
604 | 603 3
605 | 604 6
606 | 605 3
607 | 606 0
608 | 607 3
609 | 608 1
610 | 609 2
611 | 610 5
612 | 611 6
613 | 612 5
614 | 613 2
615 | 614 0
616 | 615 2
617 | 616 2
618 | 617 3
619 | 618 3
620 | 619 0
621 | 620 3
622 | 621 5
623 | 622 3
624 | 623 4
625 | 624 0
626 | 625 3
627 | 626 2
628 | 627 4
629 | 628 5
630 | 629 2
631 | 630 3
632 | 631 2
633 | 632 2
634 | 633 3
635 | 634 5
636 | 635 2
637 | 636 0
638 | 637 3
639 | 638 4
640 | 639 3
641 | 1708 3
642 | 1709 2
643 | 1710 2
644 | 1711 2
645 | 1712 2
646 | 1713 0
647 | 1714 2
648 | 1715 2
649 | 1716 2
650 | 1717 2
651 | 1718 2
652 | 1719 2
653 | 1720 2
654 | 1721 2
655 | 1722 2
656 | 1723 2
657 | 1724 2
658 | 1725 2
659 | 1726 2
660 | 1727 2
661 | 1728 3
662 | 1729 2
663 | 1730 2
664 | 1731 2
665 | 1732 2
666 | 1733 2
667 | 1734 2
668 | 1735 1
669 | 1736 2
670 | 1737 2
671 | 1738 2
672 | 1739 2
673 | 1740 2
674 | 1741 3
675 | 1742 2
676 | 1743 2
677 | 1744 2
678 | 1745 2
679 | 1746 2
680 | 1747 2
681 | 1748 2
682 | 1749 2
683 | 1750 2
684 | 1751 2
685 | 1752 2
686 | 1753 2
687 | 1754 2
688 | 1755 2
689 | 1756 2
690 | 1757 2
691 | 1758 2
692 | 1759 2
693 | 1760 2
694 | 1761 2
695 | 1762 2
696 | 1763 2
697 | 1764 5
698 | 1765 2
699 | 1766 2
700 | 1767 1
701 | 1768 1
702 | 1769 1
703 | 1770 1
704 | 1771 1
705 | 1772 1
706 | 1773 1
707 | 1774 4
708 | 1775 1
709 | 1776 1
710 | 1777 1
711 | 1778 1
712 | 1779 1
713 | 1780 1
714 | 1781 1
715 | 1782 1
716 | 1783 1
717 | 1784 1
718 | 1785 4
719 | 1786 1
720 | 1787 1
721 | 1788 1
722 | 1789 1
723 | 1790 1
724 | 1791 1
725 | 1792 3
726 | 1793 4
727 | 1794 4
728 | 1795 4
729 | 1796 4
730 | 1797 1
731 | 1798 1
732 | 1799 3
733 | 1800 1
734 | 1801 0
735 | 1802 3
736 | 1803 0
737 | 1804 2
738 | 1805 1
739 | 1806 3
740 | 1807 3
741 | 1808 3
742 | 1809 3
743 | 1810 3
744 | 1811 3
745 | 1812 3
746 | 1813 3
747 | 1814 3
748 | 1815 3
749 | 1816 3
750 | 1817 3
751 | 1818 3
752 | 1819 3
753 | 1820 3
754 | 1821 3
755 | 1822 3
756 | 1823 3
757 | 1824 5
758 | 1825 5
759 | 1826 5
760 | 1827 5
761 | 1828 5
762 | 1829 5
763 | 1830 2
764 | 1831 2
765 | 1832 2
766 | 1833 2
767 | 1834 1
768 | 1835 6
769 | 1836 6
770 | 1837 3
771 | 1838 0
772 | 1839 0
773 | 1840 5
774 | 1841 0
775 | 1842 5
776 | 1843 0
777 | 1844 3
778 | 1845 5
779 | 1846 3
780 | 1847 0
781 | 1848 0
782 | 1849 6
783 | 1850 0
784 | 1851 6
785 | 1852 3
786 | 1853 3
787 | 1854 1
788 | 1855 3
789 | 1856 1
790 | 1857 3
791 | 1858 3
792 | 1859 3
793 | 1860 3
794 | 1861 3
795 | 1862 3
796 | 1863 3
797 | 1864 3
798 | 1865 3
799 | 1866 3
800 | 1867 3
801 | 1868 3
802 | 1869 3
803 | 1870 3
804 | 1871 3
805 | 1872 3
806 | 1873 3
807 | 1874 3
808 | 1875 3
809 | 1876 3
810 | 1877 3
811 | 1878 5
812 | 1879 5
813 | 1880 5
814 | 1881 5
815 | 1882 5
816 | 1883 5
817 | 1884 5
818 | 1885 5
819 | 1886 2
820 | 1887 2
821 | 1888 2
822 | 1889 4
823 | 1890 4
824 | 1891 4
825 | 1892 0
826 | 1893 3
827 | 1894 3
828 | 1895 2
829 | 1896 5
830 | 1897 5
831 | 1898 5
832 | 1899 5
833 | 1900 6
834 | 1901 5
835 | 1902 5
836 | 1903 5
837 | 1904 5
838 | 1905 0
839 | 1906 4
840 | 1907 4
841 | 1908 4
842 | 1909 0
843 | 1910 0
844 | 1911 5
845 | 1912 0
846 | 1913 0
847 | 1914 6
848 | 1915 6
849 | 1916 6
850 | 1917 6
851 | 1918 6
852 | 1919 6
853 | 1920 0
854 | 1921 0
855 | 1922 0
856 | 1923 0
857 | 1924 3
858 | 1925 0
859 | 1926 0
860 | 1927 0
861 | 1928 3
862 | 1929 3
863 | 1930 0
864 | 1931 3
865 | 1932 3
866 | 1933 3
867 | 1934 3
868 | 1935 3
869 | 1936 3
870 | 1937 3
871 | 1938 3
872 | 1939 3
873 | 1940 3
874 | 1941 3
875 | 1942 3
876 | 1943 3
877 | 1944 3
878 | 1945 3
879 | 1946 3
880 | 1947 3
881 | 1948 3
882 | 1949 3
883 | 1950 3
884 | 1951 3
885 | 1952 3
886 | 1953 5
887 | 1954 5
888 | 1955 5
889 | 1956 5
890 | 1957 3
891 | 1958 5
892 | 1959 5
893 | 1960 5
894 | 1961 5
895 | 1962 5
896 | 1963 5
897 | 1964 4
898 | 1965 4
899 | 1966 4
900 | 1967 4
901 | 1968 4
902 | 1969 4
903 | 1970 4
904 | 1971 4
905 | 1972 6
906 | 1973 6
907 | 1974 5
908 | 1975 6
909 | 1976 6
910 | 1977 3
911 | 1978 5
912 | 1979 5
913 | 1980 5
914 | 1981 0
915 | 1982 5
916 | 1983 0
917 | 1984 4
918 | 1985 4
919 | 1986 3
920 | 1987 3
921 | 1988 3
922 | 1989 2
923 | 1990 2
924 | 1991 1
925 | 1992 3
926 | 1993 3
927 | 1994 3
928 | 1995 3
929 | 1996 3
930 | 1997 3
931 | 1998 5
932 | 1999 3
933 | 2000 3
934 | 2001 4
935 | 2002 4
936 | 2003 3
937 | 2004 3
938 | 2005 3
939 | 2006 3
940 | 2007 3
941 | 2008 3
942 | 2009 3
943 | 2010 0
944 | 2011 3
945 | 2012 3
946 | 2013 6
947 | 2014 3
948 | 2015 6
949 | 2016 0
950 | 2017 5
951 | 2018 0
952 | 2019 0
953 | 2020 4
954 | 2021 0
955 | 2022 6
956 | 2023 5
957 | 2024 5
958 | 2025 0
959 | 2026 1
960 | 2027 3
961 | 2028 3
962 | 2029 5
963 | 2030 6
964 | 2031 5
965 | 2032 3
966 | 2033 3
967 | 2034 4
968 | 2035 3
969 | 2036 3
970 | 2037 3
971 | 2038 3
972 | 2039 3
973 | 2040 4
974 | 2041 3
975 | 2042 3
976 | 2043 4
977 | 2044 3
978 | 2045 1
979 | 2046 1
980 | 2047 0
981 | 2048 1
982 | 2049 0
983 | 2050 6
984 | 2051 0
985 | 2052 0
986 | 2053 0
987 | 2054 0
988 | 2055 0
989 | 2056 0
990 | 2057 0
991 | 2058 5
992 | 2059 0
993 | 2060 5
994 | 2061 5
995 | 2062 5
996 | 2063 3
997 | 2064 3
998 | 2065 3
999 | 2066 3
1000 | 2067 3
1001 | 2068 0
1002 | 2069 0
1003 | 2070 0
1004 | 2071 2
1005 | 2072 0
1006 | 2073 0
1007 | 2074 0
1008 | 2075 3
1009 | 2076 3
1010 | 2077 3
1011 | 2078 3
1012 | 2079 1
1013 | 2080 1
1014 | 2081 1
1015 | 2082 1
1016 | 2083 2
1017 | 2084 1
1018 | 2085 1
1019 | 2086 1
1020 | 2087 1
1021 | 2088 1
1022 | 2089 0
1023 | 2090 1
1024 | 2091 3
1025 | 2092 1
1026 | 2093 1
1027 | 2094 1
1028 | 2095 1
1029 | 2096 1
1030 | 2097 0
1031 | 2098 0
1032 | 2099 0
1033 | 2100 5
1034 | 2101 5
1035 | 2102 5
1036 | 2103 5
1037 | 2104 3
1038 | 2105 5
1039 | 2106 1
1040 | 2107 1
1041 | 2108 3
1042 | 2109 6
1043 | 2110 6
1044 | 2111 5
1045 | 2112 6
1046 | 2113 2
1047 | 2114 3
1048 | 2115 3
1049 | 2116 0
1050 | 2117 3
1051 | 2118 3
1052 | 2119 3
1053 | 2120 4
1054 | 2121 4
1055 | 2122 4
1056 | 2123 4
1057 | 2124 3
1058 | 2125 3
1059 | 2126 3
1060 | 2127 4
1061 | 2128 3
1062 | 2129 3
1063 | 2130 4
1064 | 2131 0
1065 | 2132 6
1066 | 2133 0
1067 | 2134 6
1068 | 2135 6
1069 | 2136 0
1070 | 2137 0
1071 | 2138 3
1072 | 2139 3
1073 | 2140 3
1074 | 2141 3
1075 | 2142 3
1076 | 2143 1
1077 | 2144 1
1078 | 2145 1
1079 | 2146 3
1080 | 2147 3
1081 | 2148 3
1082 | 2149 3
1083 | 2150 5
1084 | 2151 6
1085 | 2152 3
1086 | 2153 4
1087 | 2154 6
1088 | 2155 0
1089 | 2156 0
1090 | 2157 6
1091 | 2158 6
1092 | 2159 6
1093 | 2160 6
1094 | 2161 6
1095 | 2162 3
1096 | 2163 3
1097 | 2164 6
1098 | 2165 6
1099 | 2166 5
1100 | 2167 2
1101 | 2168 1
1102 | 2169 2
1103 | 2170 1
1104 | 2171 0
1105 | 2172 0
1106 | 2173 6
1107 | 2174 6
1108 | 2175 2
1109 | 2176 3
1110 | 2177 3
1111 | 2178 5
1112 | 2179 0
1113 | 2180 0
1114 | 2181 0
1115 | 2182 0
1116 | 2183 0
1117 | 2184 5
1118 | 2185 5
1119 | 2186 0
1120 | 2187 3
1121 | 2188 5
1122 | 2189 0
1123 | 2190 6
1124 | 2191 3
1125 | 2192 6
1126 | 2193 0
1127 | 2194 0
1128 | 2195 0
1129 | 2196 0
1130 | 2197 0
1131 | 2198 0
1132 | 2199 0
1133 | 2200 0
1134 | 2201 0
1135 | 2202 0
1136 | 2203 0
1137 | 2204 3
1138 | 2205 3
1139 | 2206 3
1140 | 2207 3
1141 | 2208 1
1142 | 2209 6
1143 | 2210 1
1144 | 2211 0
1145 | 2212 3
1146 | 2213 3
1147 | 2214 3
1148 | 2215 3
1149 | 2216 3
1150 | 2217 6
1151 | 2218 1
1152 | 2219 0
1153 | 2220 2
1154 | 2221 2
1155 | 2222 4
1156 | 2223 4
1157 | 2224 4
1158 | 2225 4
1159 | 2226 4
1160 | 2227 5
1161 | 2228 6
1162 | 2229 3
1163 | 2230 3
1164 | 2231 0
1165 | 2232 0
1166 | 2233 0
1167 | 2234 0
1168 | 2235 5
1169 | 2236 4
1170 | 2237 4
1171 | 2238 4
1172 | 2239 4
1173 | 2240 4
1174 | 2241 3
1175 | 2242 3
1176 | 2243 3
1177 | 2244 3
1178 | 2245 3
1179 | 2246 0
1180 | 2247 3
1181 | 2248 4
1182 | 2249 4
1183 | 2250 4
1184 | 2251 1
1185 | 2252 1
1186 | 2253 3
1187 | 2254 1
1188 | 2255 1
1189 | 2256 5
1190 | 2257 1
1191 | 2258 3
1192 | 2259 4
1193 | 2260 4
1194 | 2261 4
1195 | 2262 4
1196 | 2263 4
1197 | 2264 4
1198 | 2265 4
1199 | 2266 0
1200 | 2267 0
1201 | 2268 0
1202 | 2269 5
1203 | 2270 5
1204 | 2271 5
1205 | 2272 5
1206 | 2273 5
1207 | 2274 0
1208 | 2275 5
1209 | 2276 3
1210 | 2277 0
1211 | 2278 6
1212 | 2279 2
1213 | 2280 0
1214 | 2281 5
1215 | 2282 3
1216 | 2283 3
1217 | 2284 5
1218 | 2285 5
1219 | 2286 5
1220 | 2287 5
1221 | 2288 5
1222 | 2289 4
1223 | 2290 4
1224 | 2291 0
1225 | 2292 4
1226 | 2293 0
1227 | 2294 4
1228 | 2295 0
1229 | 2296 3
1230 | 2297 4
1231 | 2298 4
1232 | 2299 4
1233 | 2300 1
1234 | 2301 3
1235 | 2302 3
1236 | 2303 3
1237 | 2304 3
1238 | 2305 3
1239 | 2306 4
1240 | 2307 2
1241 | 2308 3
1242 | 2309 3
1243 | 2310 3
1244 | 2311 0
1245 | 2312 0
1246 | 2313 2
1247 | 2314 3
1248 | 2315 3
1249 | 2316 3
1250 | 2317 3
1251 | 2318 1
1252 | 2319 1
1253 | 2320 3
1254 | 2321 0
1255 | 2322 1
1256 | 2323 4
1257 | 2324 1
1258 | 2325 1
1259 | 2326 1
1260 | 2327 1
1261 | 2328 1
1262 | 2329 1
1263 | 2330 0
1264 | 2331 1
1265 | 2332 0
1266 | 2333 0
1267 | 2334 2
1268 | 2335 4
1269 | 2336 4
1270 | 2337 4
1271 | 2338 3
1272 | 2339 3
1273 | 2340 3
1274 | 2341 4
1275 | 2342 0
1276 | 2343 3
1277 | 2344 3
1278 | 2345 3
1279 | 2346 3
1280 | 2347 0
1281 | 2348 3
1282 | 2349 3
1283 | 2350 4
1284 | 2351 4
1285 | 2352 4
1286 | 2353 4
1287 | 2354 4
1288 | 2355 4
1289 | 2356 0
1290 | 2357 4
1291 | 2358 3
1292 | 2359 2
1293 | 2360 0
1294 | 2361 3
1295 | 2362 4
1296 | 2363 5
1297 | 2364 0
1298 | 2365 2
1299 | 2366 2
1300 | 2367 3
1301 | 2368 3
1302 | 2369 3
1303 | 2370 3
1304 | 2371 3
1305 | 2372 2
1306 | 2373 3
1307 | 2374 5
1308 | 2375 5
1309 | 2376 4
1310 | 2377 1
1311 | 2378 4
1312 | 2379 4
1313 | 2380 4
1314 | 2381 3
1315 | 2382 4
1316 | 2383 4
1317 | 2384 0
1318 | 2385 4
1319 | 2386 4
1320 | 2387 4
1321 | 2388 5
1322 | 2389 2
1323 | 2390 2
1324 | 2391 2
1325 | 2392 2
1326 | 2393 4
1327 | 2394 6
1328 | 2395 6
1329 | 2396 6
1330 | 2397 6
1331 | 2398 3
1332 | 2399 4
1333 | 2400 4
1334 | 2401 4
1335 | 2402 1
1336 | 2403 3
1337 | 2404 0
1338 | 2405 3
1339 | 2406 3
1340 | 2407 5
1341 | 2408 0
1342 | 2409 2
1343 | 2410 3
1344 | 2411 3
1345 | 2412 3
1346 | 2413 3
1347 | 2414 3
1348 | 2415 2
1349 | 2416 4
1350 | 2417 4
1351 | 2418 0
1352 | 2419 0
1353 | 2420 3
1354 | 2421 2
1355 | 2422 6
1356 | 2423 6
1357 | 2424 0
1358 | 2425 3
1359 | 2426 3
1360 | 2427 3
1361 | 2428 5
1362 | 2429 1
1363 | 2430 3
1364 | 2431 4
1365 | 2432 4
1366 | 2433 2
1367 | 2434 4
1368 | 2435 4
1369 | 2436 4
1370 | 2437 3
1371 | 2438 3
1372 | 2439 2
1373 | 2440 2
1374 | 2441 2
1375 | 2442 2
1376 | 2443 2
1377 | 2444 2
1378 | 2445 2
1379 | 2446 2
1380 | 2447 2
1381 | 2448 2
1382 | 2449 0
1383 | 2450 2
1384 | 2451 2
1385 | 2452 2
1386 | 2453 0
1387 | 2454 6
1388 | 2455 6
1389 | 2456 5
1390 | 2457 6
1391 | 2458 6
1392 | 2459 3
1393 | 2460 2
1394 | 2461 6
1395 | 2462 3
1396 | 2463 4
1397 | 2464 4
1398 | 2465 4
1399 | 2466 2
1400 | 2467 6
1401 | 2468 6
1402 | 2469 0
1403 | 2470 0
1404 | 2471 3
1405 | 2472 0
1406 | 2473 4
1407 | 2474 4
1408 | 2475 3
1409 | 2476 2
1410 | 2477 3
1411 | 2478 1
1412 | 2479 6
1413 | 2480 6
1414 | 2481 5
1415 | 2482 3
1416 | 2483 4
1417 | 2484 3
1418 | 2485 5
1419 | 2486 3
1420 | 2487 1
1421 | 2488 1
1422 | 2489 3
1423 | 2490 4
1424 | 2491 5
1425 | 2492 2
1426 | 2493 3
1427 | 2494 3
1428 | 2495 3
1429 | 2496 4
1430 | 2497 5
1431 | 2498 4
1432 | 2499 0
1433 | 2500 3
1434 | 2501 3
1435 | 2502 0
1436 | 2503 2
1437 | 2504 1
1438 | 2505 1
1439 | 2506 5
1440 | 2507 2
1441 | 2508 3
1442 | 2509 3
1443 | 2510 5
1444 | 2511 0
1445 | 2512 2
1446 | 2513 3
1447 | 2514 2
1448 | 2515 2
1449 | 2516 5
1450 | 2517 5
1451 | 2518 4
1452 | 2519 3
1453 | 2520 4
1454 | 2521 3
1455 | 2522 2
1456 | 2523 2
1457 | 2524 4
1458 | 2525 2
1459 | 2526 4
1460 | 2527 5
1461 | 2528 5
1462 | 2529 3
1463 | 2530 2
1464 | 2531 3
1465 | 2532 1
1466 | 2533 0
1467 | 2534 3
1468 | 2535 3
1469 | 2536 4
1470 | 2537 5
1471 | 2538 4
1472 | 2539 3
1473 | 2540 3
1474 | 2541 3
1475 | 2542 3
1476 | 2543 3
1477 | 2544 0
1478 | 2545 1
1479 | 2546 2
1480 | 2547 4
1481 | 2548 4
1482 | 2549 4
1483 | 2550 3
1484 | 2551 3
1485 | 2552 3
1486 | 2553 5
1487 | 2554 2
1488 | 2555 3
1489 | 2556 2
1490 | 2557 2
1491 | 2558 2
1492 | 2559 3
1493 | 2560 2
1494 | 2561 2
1495 | 2562 0
1496 | 2563 4
1497 | 2564 4
1498 | 2565 3
1499 | 2566 3
1500 | 2567 3
1501 | 2568 3
1502 | 2569 3
1503 | 2570 3
1504 | 2571 3
1505 | 2572 3
1506 | 2573 3
1507 | 2574 3
1508 | 2575 0
1509 | 2576 0
1510 | 2577 3
1511 | 2578 0
1512 | 2579 3
1513 | 2580 0
1514 | 2581 2
1515 | 2582 3
1516 | 2583 4
1517 | 2584 1
1518 | 2585 2
1519 | 2586 5
1520 | 2587 4
1521 | 2588 3
1522 | 2589 3
1523 | 2590 3
1524 | 2591 1
1525 | 2592 5
1526 | 2593 3
1527 | 2594 4
1528 | 2595 3
1529 | 2596 2
1530 | 2597 2
1531 | 2598 1
1532 | 2599 3
1533 | 2600 3
1534 | 2601 3
1535 | 2602 3
1536 | 2603 3
1537 | 2604 6
1538 | 2605 3
1539 | 2606 3
1540 | 2607 3
1541 | 2608 6
1542 | 2609 3
1543 | 2610 3
1544 | 2611 3
1545 | 2612 2
1546 | 2613 3
1547 | 2614 2
1548 | 2615 4
1549 | 2616 2
1550 | 2617 4
1551 | 2618 2
1552 | 2619 2
1553 | 2620 1
1554 | 2621 5
1555 | 2622 6
1556 | 2623 4
1557 | 2624 3
1558 | 2625 3
1559 | 2626 3
1560 | 2627 2
1561 | 2628 5
1562 | 2629 3
1563 | 2630 3
1564 | 2631 4
1565 | 2632 3
1566 | 2633 3
1567 | 2634 3
1568 | 2635 3
1569 | 2636 3
1570 | 2637 4
1571 | 2638 6
1572 | 2639 0
1573 | 2640 3
1574 | 2641 2
1575 | 2642 2
1576 | 2643 2
1577 | 2644 5
1578 | 2645 4
1579 | 2646 4
1580 | 2647 4
1581 | 2648 4
1582 | 2649 6
1583 | 2650 3
1584 | 2651 2
1585 | 2652 2
1586 | 2653 0
1587 | 2654 2
1588 | 2655 2
1589 | 2656 2
1590 | 2657 2
1591 | 2658 2
1592 | 2659 3
1593 | 2660 4
1594 | 2661 4
1595 | 2662 4
1596 | 2663 3
1597 | 2664 3
1598 | 2665 4
1599 | 2666 4
1600 | 2667 3
1601 | 2668 3
1602 | 2669 3
1603 | 2670 4
1604 | 2671 4
1605 | 2672 4
1606 | 2673 4
1607 | 2674 4
1608 | 2675 4
1609 | 2676 3
1610 | 2677 4
1611 | 2678 4
1612 | 2679 4
1613 | 2680 4
1614 | 2681 4
1615 | 2682 4
1616 | 2683 4
1617 | 2684 4
1618 | 2685 2
1619 | 2686 3
1620 | 2687 3
1621 | 2688 3
1622 | 2689 2
1623 | 2690 6
1624 | 2691 2
1625 | 2692 3
1626 | 2693 3
1627 | 2694 4
1628 | 2695 4
1629 | 2696 3
1630 | 2697 3
1631 | 2698 3
1632 | 2699 3
1633 | 2700 3
1634 | 2701 3
1635 | 2702 0
1636 | 2703 3
1637 | 2704 3
1638 | 2705 3
1639 | 2706 3
1640 | 2707 3
1641 |
--------------------------------------------------------------------------------
/semisupervised/data/cora/test.txt:
--------------------------------------------------------------------------------
1 | 1708
2 | 1709
3 | 1710
4 | 1711
5 | 1712
6 | 1713
7 | 1714
8 | 1715
9 | 1716
10 | 1717
11 | 1718
12 | 1719
13 | 1720
14 | 1721
15 | 1722
16 | 1723
17 | 1724
18 | 1725
19 | 1726
20 | 1727
21 | 1728
22 | 1729
23 | 1730
24 | 1731
25 | 1732
26 | 1733
27 | 1734
28 | 1735
29 | 1736
30 | 1737
31 | 1738
32 | 1739
33 | 1740
34 | 1741
35 | 1742
36 | 1743
37 | 1744
38 | 1745
39 | 1746
40 | 1747
41 | 1748
42 | 1749
43 | 1750
44 | 1751
45 | 1752
46 | 1753
47 | 1754
48 | 1755
49 | 1756
50 | 1757
51 | 1758
52 | 1759
53 | 1760
54 | 1761
55 | 1762
56 | 1763
57 | 1764
58 | 1765
59 | 1766
60 | 1767
61 | 1768
62 | 1769
63 | 1770
64 | 1771
65 | 1772
66 | 1773
67 | 1774
68 | 1775
69 | 1776
70 | 1777
71 | 1778
72 | 1779
73 | 1780
74 | 1781
75 | 1782
76 | 1783
77 | 1784
78 | 1785
79 | 1786
80 | 1787
81 | 1788
82 | 1789
83 | 1790
84 | 1791
85 | 1792
86 | 1793
87 | 1794
88 | 1795
89 | 1796
90 | 1797
91 | 1798
92 | 1799
93 | 1800
94 | 1801
95 | 1802
96 | 1803
97 | 1804
98 | 1805
99 | 1806
100 | 1807
101 | 1808
102 | 1809
103 | 1810
104 | 1811
105 | 1812
106 | 1813
107 | 1814
108 | 1815
109 | 1816
110 | 1817
111 | 1818
112 | 1819
113 | 1820
114 | 1821
115 | 1822
116 | 1823
117 | 1824
118 | 1825
119 | 1826
120 | 1827
121 | 1828
122 | 1829
123 | 1830
124 | 1831
125 | 1832
126 | 1833
127 | 1834
128 | 1835
129 | 1836
130 | 1837
131 | 1838
132 | 1839
133 | 1840
134 | 1841
135 | 1842
136 | 1843
137 | 1844
138 | 1845
139 | 1846
140 | 1847
141 | 1848
142 | 1849
143 | 1850
144 | 1851
145 | 1852
146 | 1853
147 | 1854
148 | 1855
149 | 1856
150 | 1857
151 | 1858
152 | 1859
153 | 1860
154 | 1861
155 | 1862
156 | 1863
157 | 1864
158 | 1865
159 | 1866
160 | 1867
161 | 1868
162 | 1869
163 | 1870
164 | 1871
165 | 1872
166 | 1873
167 | 1874
168 | 1875
169 | 1876
170 | 1877
171 | 1878
172 | 1879
173 | 1880
174 | 1881
175 | 1882
176 | 1883
177 | 1884
178 | 1885
179 | 1886
180 | 1887
181 | 1888
182 | 1889
183 | 1890
184 | 1891
185 | 1892
186 | 1893
187 | 1894
188 | 1895
189 | 1896
190 | 1897
191 | 1898
192 | 1899
193 | 1900
194 | 1901
195 | 1902
196 | 1903
197 | 1904
198 | 1905
199 | 1906
200 | 1907
201 | 1908
202 | 1909
203 | 1910
204 | 1911
205 | 1912
206 | 1913
207 | 1914
208 | 1915
209 | 1916
210 | 1917
211 | 1918
212 | 1919
213 | 1920
214 | 1921
215 | 1922
216 | 1923
217 | 1924
218 | 1925
219 | 1926
220 | 1927
221 | 1928
222 | 1929
223 | 1930
224 | 1931
225 | 1932
226 | 1933
227 | 1934
228 | 1935
229 | 1936
230 | 1937
231 | 1938
232 | 1939
233 | 1940
234 | 1941
235 | 1942
236 | 1943
237 | 1944
238 | 1945
239 | 1946
240 | 1947
241 | 1948
242 | 1949
243 | 1950
244 | 1951
245 | 1952
246 | 1953
247 | 1954
248 | 1955
249 | 1956
250 | 1957
251 | 1958
252 | 1959
253 | 1960
254 | 1961
255 | 1962
256 | 1963
257 | 1964
258 | 1965
259 | 1966
260 | 1967
261 | 1968
262 | 1969
263 | 1970
264 | 1971
265 | 1972
266 | 1973
267 | 1974
268 | 1975
269 | 1976
270 | 1977
271 | 1978
272 | 1979
273 | 1980
274 | 1981
275 | 1982
276 | 1983
277 | 1984
278 | 1985
279 | 1986
280 | 1987
281 | 1988
282 | 1989
283 | 1990
284 | 1991
285 | 1992
286 | 1993
287 | 1994
288 | 1995
289 | 1996
290 | 1997
291 | 1998
292 | 1999
293 | 2000
294 | 2001
295 | 2002
296 | 2003
297 | 2004
298 | 2005
299 | 2006
300 | 2007
301 | 2008
302 | 2009
303 | 2010
304 | 2011
305 | 2012
306 | 2013
307 | 2014
308 | 2015
309 | 2016
310 | 2017
311 | 2018
312 | 2019
313 | 2020
314 | 2021
315 | 2022
316 | 2023
317 | 2024
318 | 2025
319 | 2026
320 | 2027
321 | 2028
322 | 2029
323 | 2030
324 | 2031
325 | 2032
326 | 2033
327 | 2034
328 | 2035
329 | 2036
330 | 2037
331 | 2038
332 | 2039
333 | 2040
334 | 2041
335 | 2042
336 | 2043
337 | 2044
338 | 2045
339 | 2046
340 | 2047
341 | 2048
342 | 2049
343 | 2050
344 | 2051
345 | 2052
346 | 2053
347 | 2054
348 | 2055
349 | 2056
350 | 2057
351 | 2058
352 | 2059
353 | 2060
354 | 2061
355 | 2062
356 | 2063
357 | 2064
358 | 2065
359 | 2066
360 | 2067
361 | 2068
362 | 2069
363 | 2070
364 | 2071
365 | 2072
366 | 2073
367 | 2074
368 | 2075
369 | 2076
370 | 2077
371 | 2078
372 | 2079
373 | 2080
374 | 2081
375 | 2082
376 | 2083
377 | 2084
378 | 2085
379 | 2086
380 | 2087
381 | 2088
382 | 2089
383 | 2090
384 | 2091
385 | 2092
386 | 2093
387 | 2094
388 | 2095
389 | 2096
390 | 2097
391 | 2098
392 | 2099
393 | 2100
394 | 2101
395 | 2102
396 | 2103
397 | 2104
398 | 2105
399 | 2106
400 | 2107
401 | 2108
402 | 2109
403 | 2110
404 | 2111
405 | 2112
406 | 2113
407 | 2114
408 | 2115
409 | 2116
410 | 2117
411 | 2118
412 | 2119
413 | 2120
414 | 2121
415 | 2122
416 | 2123
417 | 2124
418 | 2125
419 | 2126
420 | 2127
421 | 2128
422 | 2129
423 | 2130
424 | 2131
425 | 2132
426 | 2133
427 | 2134
428 | 2135
429 | 2136
430 | 2137
431 | 2138
432 | 2139
433 | 2140
434 | 2141
435 | 2142
436 | 2143
437 | 2144
438 | 2145
439 | 2146
440 | 2147
441 | 2148
442 | 2149
443 | 2150
444 | 2151
445 | 2152
446 | 2153
447 | 2154
448 | 2155
449 | 2156
450 | 2157
451 | 2158
452 | 2159
453 | 2160
454 | 2161
455 | 2162
456 | 2163
457 | 2164
458 | 2165
459 | 2166
460 | 2167
461 | 2168
462 | 2169
463 | 2170
464 | 2171
465 | 2172
466 | 2173
467 | 2174
468 | 2175
469 | 2176
470 | 2177
471 | 2178
472 | 2179
473 | 2180
474 | 2181
475 | 2182
476 | 2183
477 | 2184
478 | 2185
479 | 2186
480 | 2187
481 | 2188
482 | 2189
483 | 2190
484 | 2191
485 | 2192
486 | 2193
487 | 2194
488 | 2195
489 | 2196
490 | 2197
491 | 2198
492 | 2199
493 | 2200
494 | 2201
495 | 2202
496 | 2203
497 | 2204
498 | 2205
499 | 2206
500 | 2207
501 | 2208
502 | 2209
503 | 2210
504 | 2211
505 | 2212
506 | 2213
507 | 2214
508 | 2215
509 | 2216
510 | 2217
511 | 2218
512 | 2219
513 | 2220
514 | 2221
515 | 2222
516 | 2223
517 | 2224
518 | 2225
519 | 2226
520 | 2227
521 | 2228
522 | 2229
523 | 2230
524 | 2231
525 | 2232
526 | 2233
527 | 2234
528 | 2235
529 | 2236
530 | 2237
531 | 2238
532 | 2239
533 | 2240
534 | 2241
535 | 2242
536 | 2243
537 | 2244
538 | 2245
539 | 2246
540 | 2247
541 | 2248
542 | 2249
543 | 2250
544 | 2251
545 | 2252
546 | 2253
547 | 2254
548 | 2255
549 | 2256
550 | 2257
551 | 2258
552 | 2259
553 | 2260
554 | 2261
555 | 2262
556 | 2263
557 | 2264
558 | 2265
559 | 2266
560 | 2267
561 | 2268
562 | 2269
563 | 2270
564 | 2271
565 | 2272
566 | 2273
567 | 2274
568 | 2275
569 | 2276
570 | 2277
571 | 2278
572 | 2279
573 | 2280
574 | 2281
575 | 2282
576 | 2283
577 | 2284
578 | 2285
579 | 2286
580 | 2287
581 | 2288
582 | 2289
583 | 2290
584 | 2291
585 | 2292
586 | 2293
587 | 2294
588 | 2295
589 | 2296
590 | 2297
591 | 2298
592 | 2299
593 | 2300
594 | 2301
595 | 2302
596 | 2303
597 | 2304
598 | 2305
599 | 2306
600 | 2307
601 | 2308
602 | 2309
603 | 2310
604 | 2311
605 | 2312
606 | 2313
607 | 2314
608 | 2315
609 | 2316
610 | 2317
611 | 2318
612 | 2319
613 | 2320
614 | 2321
615 | 2322
616 | 2323
617 | 2324
618 | 2325
619 | 2326
620 | 2327
621 | 2328
622 | 2329
623 | 2330
624 | 2331
625 | 2332
626 | 2333
627 | 2334
628 | 2335
629 | 2336
630 | 2337
631 | 2338
632 | 2339
633 | 2340
634 | 2341
635 | 2342
636 | 2343
637 | 2344
638 | 2345
639 | 2346
640 | 2347
641 | 2348
642 | 2349
643 | 2350
644 | 2351
645 | 2352
646 | 2353
647 | 2354
648 | 2355
649 | 2356
650 | 2357
651 | 2358
652 | 2359
653 | 2360
654 | 2361
655 | 2362
656 | 2363
657 | 2364
658 | 2365
659 | 2366
660 | 2367
661 | 2368
662 | 2369
663 | 2370
664 | 2371
665 | 2372
666 | 2373
667 | 2374
668 | 2375
669 | 2376
670 | 2377
671 | 2378
672 | 2379
673 | 2380
674 | 2381
675 | 2382
676 | 2383
677 | 2384
678 | 2385
679 | 2386
680 | 2387
681 | 2388
682 | 2389
683 | 2390
684 | 2391
685 | 2392
686 | 2393
687 | 2394
688 | 2395
689 | 2396
690 | 2397
691 | 2398
692 | 2399
693 | 2400
694 | 2401
695 | 2402
696 | 2403
697 | 2404
698 | 2405
699 | 2406
700 | 2407
701 | 2408
702 | 2409
703 | 2410
704 | 2411
705 | 2412
706 | 2413
707 | 2414
708 | 2415
709 | 2416
710 | 2417
711 | 2418
712 | 2419
713 | 2420
714 | 2421
715 | 2422
716 | 2423
717 | 2424
718 | 2425
719 | 2426
720 | 2427
721 | 2428
722 | 2429
723 | 2430
724 | 2431
725 | 2432
726 | 2433
727 | 2434
728 | 2435
729 | 2436
730 | 2437
731 | 2438
732 | 2439
733 | 2440
734 | 2441
735 | 2442
736 | 2443
737 | 2444
738 | 2445
739 | 2446
740 | 2447
741 | 2448
742 | 2449
743 | 2450
744 | 2451
745 | 2452
746 | 2453
747 | 2454
748 | 2455
749 | 2456
750 | 2457
751 | 2458
752 | 2459
753 | 2460
754 | 2461
755 | 2462
756 | 2463
757 | 2464
758 | 2465
759 | 2466
760 | 2467
761 | 2468
762 | 2469
763 | 2470
764 | 2471
765 | 2472
766 | 2473
767 | 2474
768 | 2475
769 | 2476
770 | 2477
771 | 2478
772 | 2479
773 | 2480
774 | 2481
775 | 2482
776 | 2483
777 | 2484
778 | 2485
779 | 2486
780 | 2487
781 | 2488
782 | 2489
783 | 2490
784 | 2491
785 | 2492
786 | 2493
787 | 2494
788 | 2495
789 | 2496
790 | 2497
791 | 2498
792 | 2499
793 | 2500
794 | 2501
795 | 2502
796 | 2503
797 | 2504
798 | 2505
799 | 2506
800 | 2507
801 | 2508
802 | 2509
803 | 2510
804 | 2511
805 | 2512
806 | 2513
807 | 2514
808 | 2515
809 | 2516
810 | 2517
811 | 2518
812 | 2519
813 | 2520
814 | 2521
815 | 2522
816 | 2523
817 | 2524
818 | 2525
819 | 2526
820 | 2527
821 | 2528
822 | 2529
823 | 2530
824 | 2531
825 | 2532
826 | 2533
827 | 2534
828 | 2535
829 | 2536
830 | 2537
831 | 2538
832 | 2539
833 | 2540
834 | 2541
835 | 2542
836 | 2543
837 | 2544
838 | 2545
839 | 2546
840 | 2547
841 | 2548
842 | 2549
843 | 2550
844 | 2551
845 | 2552
846 | 2553
847 | 2554
848 | 2555
849 | 2556
850 | 2557
851 | 2558
852 | 2559
853 | 2560
854 | 2561
855 | 2562
856 | 2563
857 | 2564
858 | 2565
859 | 2566
860 | 2567
861 | 2568
862 | 2569
863 | 2570
864 | 2571
865 | 2572
866 | 2573
867 | 2574
868 | 2575
869 | 2576
870 | 2577
871 | 2578
872 | 2579
873 | 2580
874 | 2581
875 | 2582
876 | 2583
877 | 2584
878 | 2585
879 | 2586
880 | 2587
881 | 2588
882 | 2589
883 | 2590
884 | 2591
885 | 2592
886 | 2593
887 | 2594
888 | 2595
889 | 2596
890 | 2597
891 | 2598
892 | 2599
893 | 2600
894 | 2601
895 | 2602
896 | 2603
897 | 2604
898 | 2605
899 | 2606
900 | 2607
901 | 2608
902 | 2609
903 | 2610
904 | 2611
905 | 2612
906 | 2613
907 | 2614
908 | 2615
909 | 2616
910 | 2617
911 | 2618
912 | 2619
913 | 2620
914 | 2621
915 | 2622
916 | 2623
917 | 2624
918 | 2625
919 | 2626
920 | 2627
921 | 2628
922 | 2629
923 | 2630
924 | 2631
925 | 2632
926 | 2633
927 | 2634
928 | 2635
929 | 2636
930 | 2637
931 | 2638
932 | 2639
933 | 2640
934 | 2641
935 | 2642
936 | 2643
937 | 2644
938 | 2645
939 | 2646
940 | 2647
941 | 2648
942 | 2649
943 | 2650
944 | 2651
945 | 2652
946 | 2653
947 | 2654
948 | 2655
949 | 2656
950 | 2657
951 | 2658
952 | 2659
953 | 2660
954 | 2661
955 | 2662
956 | 2663
957 | 2664
958 | 2665
959 | 2666
960 | 2667
961 | 2668
962 | 2669
963 | 2670
964 | 2671
965 | 2672
966 | 2673
967 | 2674
968 | 2675
969 | 2676
970 | 2677
971 | 2678
972 | 2679
973 | 2680
974 | 2681
975 | 2682
976 | 2683
977 | 2684
978 | 2685
979 | 2686
980 | 2687
981 | 2688
982 | 2689
983 | 2690
984 | 2691
985 | 2692
986 | 2693
987 | 2694
988 | 2695
989 | 2696
990 | 2697
991 | 2698
992 | 2699
993 | 2700
994 | 2701
995 | 2702
996 | 2703
997 | 2704
998 | 2705
999 | 2706
1000 | 2707
1001 |
--------------------------------------------------------------------------------
/semisupervised/data/cora/train.txt:
--------------------------------------------------------------------------------
1 | 0
2 | 1
3 | 2
4 | 3
5 | 4
6 | 5
7 | 6
8 | 7
9 | 8
10 | 9
11 | 10
12 | 11
13 | 12
14 | 13
15 | 14
16 | 15
17 | 16
18 | 17
19 | 18
20 | 19
21 | 20
22 | 21
23 | 22
24 | 23
25 | 24
26 | 25
27 | 26
28 | 27
29 | 28
30 | 29
31 | 30
32 | 31
33 | 32
34 | 33
35 | 34
36 | 35
37 | 36
38 | 37
39 | 38
40 | 39
41 | 40
42 | 41
43 | 42
44 | 43
45 | 44
46 | 45
47 | 46
48 | 47
49 | 48
50 | 49
51 | 50
52 | 51
53 | 52
54 | 53
55 | 54
56 | 55
57 | 56
58 | 57
59 | 58
60 | 59
61 | 60
62 | 61
63 | 62
64 | 63
65 | 64
66 | 65
67 | 66
68 | 67
69 | 68
70 | 69
71 | 70
72 | 71
73 | 72
74 | 73
75 | 74
76 | 75
77 | 76
78 | 77
79 | 78
80 | 79
81 | 80
82 | 81
83 | 82
84 | 83
85 | 84
86 | 85
87 | 86
88 | 87
89 | 88
90 | 89
91 | 90
92 | 91
93 | 92
94 | 93
95 | 94
96 | 95
97 | 96
98 | 97
99 | 98
100 | 99
101 | 100
102 | 101
103 | 102
104 | 103
105 | 104
106 | 105
107 | 106
108 | 107
109 | 108
110 | 109
111 | 110
112 | 111
113 | 112
114 | 113
115 | 114
116 | 115
117 | 116
118 | 117
119 | 118
120 | 119
121 | 120
122 | 121
123 | 122
124 | 123
125 | 124
126 | 125
127 | 126
128 | 127
129 | 128
130 | 129
131 | 130
132 | 131
133 | 132
134 | 133
135 | 134
136 | 135
137 | 136
138 | 137
139 | 138
140 | 139
141 |
--------------------------------------------------------------------------------
/semisupervised/data/pubmed/dev.txt:
--------------------------------------------------------------------------------
1 | 60
2 | 61
3 | 62
4 | 63
5 | 64
6 | 65
7 | 66
8 | 67
9 | 68
10 | 69
11 | 70
12 | 71
13 | 72
14 | 73
15 | 74
16 | 75
17 | 76
18 | 77
19 | 78
20 | 79
21 | 80
22 | 81
23 | 82
24 | 83
25 | 84
26 | 85
27 | 86
28 | 87
29 | 88
30 | 89
31 | 90
32 | 91
33 | 92
34 | 93
35 | 94
36 | 95
37 | 96
38 | 97
39 | 98
40 | 99
41 | 100
42 | 101
43 | 102
44 | 103
45 | 104
46 | 105
47 | 106
48 | 107
49 | 108
50 | 109
51 | 110
52 | 111
53 | 112
54 | 113
55 | 114
56 | 115
57 | 116
58 | 117
59 | 118
60 | 119
61 | 120
62 | 121
63 | 122
64 | 123
65 | 124
66 | 125
67 | 126
68 | 127
69 | 128
70 | 129
71 | 130
72 | 131
73 | 132
74 | 133
75 | 134
76 | 135
77 | 136
78 | 137
79 | 138
80 | 139
81 | 140
82 | 141
83 | 142
84 | 143
85 | 144
86 | 145
87 | 146
88 | 147
89 | 148
90 | 149
91 | 150
92 | 151
93 | 152
94 | 153
95 | 154
96 | 155
97 | 156
98 | 157
99 | 158
100 | 159
101 | 160
102 | 161
103 | 162
104 | 163
105 | 164
106 | 165
107 | 166
108 | 167
109 | 168
110 | 169
111 | 170
112 | 171
113 | 172
114 | 173
115 | 174
116 | 175
117 | 176
118 | 177
119 | 178
120 | 179
121 | 180
122 | 181
123 | 182
124 | 183
125 | 184
126 | 185
127 | 186
128 | 187
129 | 188
130 | 189
131 | 190
132 | 191
133 | 192
134 | 193
135 | 194
136 | 195
137 | 196
138 | 197
139 | 198
140 | 199
141 | 200
142 | 201
143 | 202
144 | 203
145 | 204
146 | 205
147 | 206
148 | 207
149 | 208
150 | 209
151 | 210
152 | 211
153 | 212
154 | 213
155 | 214
156 | 215
157 | 216
158 | 217
159 | 218
160 | 219
161 | 220
162 | 221
163 | 222
164 | 223
165 | 224
166 | 225
167 | 226
168 | 227
169 | 228
170 | 229
171 | 230
172 | 231
173 | 232
174 | 233
175 | 234
176 | 235
177 | 236
178 | 237
179 | 238
180 | 239
181 | 240
182 | 241
183 | 242
184 | 243
185 | 244
186 | 245
187 | 246
188 | 247
189 | 248
190 | 249
191 | 250
192 | 251
193 | 252
194 | 253
195 | 254
196 | 255
197 | 256
198 | 257
199 | 258
200 | 259
201 | 260
202 | 261
203 | 262
204 | 263
205 | 264
206 | 265
207 | 266
208 | 267
209 | 268
210 | 269
211 | 270
212 | 271
213 | 272
214 | 273
215 | 274
216 | 275
217 | 276
218 | 277
219 | 278
220 | 279
221 | 280
222 | 281
223 | 282
224 | 283
225 | 284
226 | 285
227 | 286
228 | 287
229 | 288
230 | 289
231 | 290
232 | 291
233 | 292
234 | 293
235 | 294
236 | 295
237 | 296
238 | 297
239 | 298
240 | 299
241 | 300
242 | 301
243 | 302
244 | 303
245 | 304
246 | 305
247 | 306
248 | 307
249 | 308
250 | 309
251 | 310
252 | 311
253 | 312
254 | 313
255 | 314
256 | 315
257 | 316
258 | 317
259 | 318
260 | 319
261 | 320
262 | 321
263 | 322
264 | 323
265 | 324
266 | 325
267 | 326
268 | 327
269 | 328
270 | 329
271 | 330
272 | 331
273 | 332
274 | 333
275 | 334
276 | 335
277 | 336
278 | 337
279 | 338
280 | 339
281 | 340
282 | 341
283 | 342
284 | 343
285 | 344
286 | 345
287 | 346
288 | 347
289 | 348
290 | 349
291 | 350
292 | 351
293 | 352
294 | 353
295 | 354
296 | 355
297 | 356
298 | 357
299 | 358
300 | 359
301 | 360
302 | 361
303 | 362
304 | 363
305 | 364
306 | 365
307 | 366
308 | 367
309 | 368
310 | 369
311 | 370
312 | 371
313 | 372
314 | 373
315 | 374
316 | 375
317 | 376
318 | 377
319 | 378
320 | 379
321 | 380
322 | 381
323 | 382
324 | 383
325 | 384
326 | 385
327 | 386
328 | 387
329 | 388
330 | 389
331 | 390
332 | 391
333 | 392
334 | 393
335 | 394
336 | 395
337 | 396
338 | 397
339 | 398
340 | 399
341 | 400
342 | 401
343 | 402
344 | 403
345 | 404
346 | 405
347 | 406
348 | 407
349 | 408
350 | 409
351 | 410
352 | 411
353 | 412
354 | 413
355 | 414
356 | 415
357 | 416
358 | 417
359 | 418
360 | 419
361 | 420
362 | 421
363 | 422
364 | 423
365 | 424
366 | 425
367 | 426
368 | 427
369 | 428
370 | 429
371 | 430
372 | 431
373 | 432
374 | 433
375 | 434
376 | 435
377 | 436
378 | 437
379 | 438
380 | 439
381 | 440
382 | 441
383 | 442
384 | 443
385 | 444
386 | 445
387 | 446
388 | 447
389 | 448
390 | 449
391 | 450
392 | 451
393 | 452
394 | 453
395 | 454
396 | 455
397 | 456
398 | 457
399 | 458
400 | 459
401 | 460
402 | 461
403 | 462
404 | 463
405 | 464
406 | 465
407 | 466
408 | 467
409 | 468
410 | 469
411 | 470
412 | 471
413 | 472
414 | 473
415 | 474
416 | 475
417 | 476
418 | 477
419 | 478
420 | 479
421 | 480
422 | 481
423 | 482
424 | 483
425 | 484
426 | 485
427 | 486
428 | 487
429 | 488
430 | 489
431 | 490
432 | 491
433 | 492
434 | 493
435 | 494
436 | 495
437 | 496
438 | 497
439 | 498
440 | 499
441 | 500
442 | 501
443 | 502
444 | 503
445 | 504
446 | 505
447 | 506
448 | 507
449 | 508
450 | 509
451 | 510
452 | 511
453 | 512
454 | 513
455 | 514
456 | 515
457 | 516
458 | 517
459 | 518
460 | 519
461 | 520
462 | 521
463 | 522
464 | 523
465 | 524
466 | 525
467 | 526
468 | 527
469 | 528
470 | 529
471 | 530
472 | 531
473 | 532
474 | 533
475 | 534
476 | 535
477 | 536
478 | 537
479 | 538
480 | 539
481 | 540
482 | 541
483 | 542
484 | 543
485 | 544
486 | 545
487 | 546
488 | 547
489 | 548
490 | 549
491 | 550
492 | 551
493 | 552
494 | 553
495 | 554
496 | 555
497 | 556
498 | 557
499 | 558
500 | 559
501 |
--------------------------------------------------------------------------------
/semisupervised/data/pubmed/label.txt:
--------------------------------------------------------------------------------
1 | 0 1
2 | 1 1
3 | 2 0
4 | 3 2
5 | 4 1
6 | 5 2
7 | 6 2
8 | 7 1
9 | 8 2
10 | 9 1
11 | 10 2
12 | 11 2
13 | 12 2
14 | 13 2
15 | 14 2
16 | 15 0
17 | 16 1
18 | 17 2
19 | 18 1
20 | 19 2
21 | 20 2
22 | 21 1
23 | 22 2
24 | 23 2
25 | 24 2
26 | 25 1
27 | 26 2
28 | 27 2
29 | 28 2
30 | 29 1
31 | 30 1
32 | 31 1
33 | 32 2
34 | 33 1
35 | 34 0
36 | 35 0
37 | 36 1
38 | 37 1
39 | 38 0
40 | 39 2
41 | 40 0
42 | 41 1
43 | 42 0
44 | 43 1
45 | 44 1
46 | 45 1
47 | 46 1
48 | 47 0
49 | 48 0
50 | 49 0
51 | 50 0
52 | 51 0
53 | 52 0
54 | 53 0
55 | 54 0
56 | 55 0
57 | 56 0
58 | 57 0
59 | 58 0
60 | 59 0
61 | 60 2
62 | 61 2
63 | 62 1
64 | 63 2
65 | 64 1
66 | 65 1
67 | 66 2
68 | 67 1
69 | 68 0
70 | 69 1
71 | 70 0
72 | 71 2
73 | 72 0
74 | 73 2
75 | 74 1
76 | 75 2
77 | 76 2
78 | 77 0
79 | 78 0
80 | 79 0
81 | 80 0
82 | 81 0
83 | 82 1
84 | 83 2
85 | 84 1
86 | 85 2
87 | 86 1
88 | 87 2
89 | 88 1
90 | 89 1
91 | 90 0
92 | 91 2
93 | 92 1
94 | 93 2
95 | 94 0
96 | 95 0
97 | 96 1
98 | 97 2
99 | 98 1
100 | 99 1
101 | 100 1
102 | 101 0
103 | 102 2
104 | 103 2
105 | 104 2
106 | 105 1
107 | 106 0
108 | 107 2
109 | 108 2
110 | 109 2
111 | 110 0
112 | 111 2
113 | 112 1
114 | 113 1
115 | 114 1
116 | 115 0
117 | 116 2
118 | 117 2
119 | 118 1
120 | 119 1
121 | 120 1
122 | 121 0
123 | 122 2
124 | 123 0
125 | 124 2
126 | 125 2
127 | 126 0
128 | 127 0
129 | 128 2
130 | 129 2
131 | 130 0
132 | 131 2
133 | 132 0
134 | 133 0
135 | 134 1
136 | 135 2
137 | 136 0
138 | 137 2
139 | 138 1
140 | 139 0
141 | 140 1
142 | 141 0
143 | 142 0
144 | 143 2
145 | 144 2
146 | 145 2
147 | 146 2
148 | 147 1
149 | 148 2
150 | 149 2
151 | 150 1
152 | 151 0
153 | 152 2
154 | 153 0
155 | 154 1
156 | 155 0
157 | 156 2
158 | 157 1
159 | 158 1
160 | 159 1
161 | 160 1
162 | 161 1
163 | 162 2
164 | 163 2
165 | 164 1
166 | 165 1
167 | 166 1
168 | 167 2
169 | 168 1
170 | 169 0
171 | 170 1
172 | 171 1
173 | 172 1
174 | 173 0
175 | 174 0
176 | 175 2
177 | 176 2
178 | 177 2
179 | 178 1
180 | 179 2
181 | 180 1
182 | 181 2
183 | 182 1
184 | 183 1
185 | 184 1
186 | 185 1
187 | 186 2
188 | 187 2
189 | 188 1
190 | 189 2
191 | 190 2
192 | 191 1
193 | 192 2
194 | 193 1
195 | 194 0
196 | 195 2
197 | 196 1
198 | 197 1
199 | 198 2
200 | 199 2
201 | 200 2
202 | 201 2
203 | 202 1
204 | 203 1
205 | 204 1
206 | 205 2
207 | 206 0
208 | 207 0
209 | 208 2
210 | 209 2
211 | 210 2
212 | 211 2
213 | 212 1
214 | 213 2
215 | 214 1
216 | 215 1
217 | 216 1
218 | 217 1
219 | 218 2
220 | 219 1
221 | 220 2
222 | 221 1
223 | 222 1
224 | 223 0
225 | 224 2
226 | 225 2
227 | 226 2
228 | 227 2
229 | 228 2
230 | 229 2
231 | 230 0
232 | 231 1
233 | 232 1
234 | 233 0
235 | 234 0
236 | 235 1
237 | 236 2
238 | 237 2
239 | 238 2
240 | 239 2
241 | 240 0
242 | 241 1
243 | 242 2
244 | 243 1
245 | 244 0
246 | 245 1
247 | 246 2
248 | 247 2
249 | 248 0
250 | 249 2
251 | 250 1
252 | 251 2
253 | 252 0
254 | 253 1
255 | 254 1
256 | 255 0
257 | 256 2
258 | 257 0
259 | 258 2
260 | 259 2
261 | 260 2
262 | 261 0
263 | 262 0
264 | 263 1
265 | 264 2
266 | 265 2
267 | 266 1
268 | 267 1
269 | 268 2
270 | 269 0
271 | 270 2
272 | 271 2
273 | 272 2
274 | 273 1
275 | 274 2
276 | 275 1
277 | 276 1
278 | 277 1
279 | 278 2
280 | 279 1
281 | 280 1
282 | 281 2
283 | 282 2
284 | 283 2
285 | 284 1
286 | 285 0
287 | 286 2
288 | 287 2
289 | 288 2
290 | 289 2
291 | 290 1
292 | 291 1
293 | 292 2
294 | 293 2
295 | 294 2
296 | 295 2
297 | 296 0
298 | 297 0
299 | 298 2
300 | 299 1
301 | 300 1
302 | 301 0
303 | 302 1
304 | 303 2
305 | 304 1
306 | 305 0
307 | 306 2
308 | 307 1
309 | 308 2
310 | 309 0
311 | 310 1
312 | 311 2
313 | 312 2
314 | 313 1
315 | 314 1
316 | 315 2
317 | 316 2
318 | 317 2
319 | 318 0
320 | 319 1
321 | 320 2
322 | 321 1
323 | 322 2
324 | 323 0
325 | 324 1
326 | 325 1
327 | 326 2
328 | 327 1
329 | 328 0
330 | 329 1
331 | 330 2
332 | 331 2
333 | 332 1
334 | 333 2
335 | 334 0
336 | 335 1
337 | 336 2
338 | 337 2
339 | 338 2
340 | 339 2
341 | 340 1
342 | 341 2
343 | 342 2
344 | 343 2
345 | 344 2
346 | 345 2
347 | 346 1
348 | 347 1
349 | 348 2
350 | 349 2
351 | 350 1
352 | 351 1
353 | 352 1
354 | 353 2
355 | 354 1
356 | 355 1
357 | 356 1
358 | 357 1
359 | 358 2
360 | 359 1
361 | 360 1
362 | 361 2
363 | 362 2
364 | 363 0
365 | 364 0
366 | 365 2
367 | 366 1
368 | 367 2
369 | 368 2
370 | 369 1
371 | 370 1
372 | 371 1
373 | 372 0
374 | 373 1
375 | 374 2
376 | 375 2
377 | 376 1
378 | 377 1
379 | 378 2
380 | 379 1
381 | 380 1
382 | 381 1
383 | 382 2
384 | 383 0
385 | 384 1
386 | 385 0
387 | 386 2
388 | 387 2
389 | 388 2
390 | 389 1
391 | 390 2
392 | 391 1
393 | 392 1
394 | 393 1
395 | 394 1
396 | 395 2
397 | 396 2
398 | 397 1
399 | 398 0
400 | 399 1
401 | 400 1
402 | 401 1
403 | 402 2
404 | 403 1
405 | 404 1
406 | 405 1
407 | 406 0
408 | 407 1
409 | 408 1
410 | 409 0
411 | 410 2
412 | 411 1
413 | 412 2
414 | 413 0
415 | 414 1
416 | 415 0
417 | 416 1
418 | 417 1
419 | 418 2
420 | 419 2
421 | 420 2
422 | 421 2
423 | 422 2
424 | 423 1
425 | 424 2
426 | 425 1
427 | 426 1
428 | 427 2
429 | 428 1
430 | 429 0
431 | 430 1
432 | 431 1
433 | 432 1
434 | 433 1
435 | 434 1
436 | 435 1
437 | 436 2
438 | 437 0
439 | 438 1
440 | 439 1
441 | 440 1
442 | 441 2
443 | 442 2
444 | 443 2
445 | 444 2
446 | 445 1
447 | 446 1
448 | 447 1
449 | 448 1
450 | 449 0
451 | 450 2
452 | 451 1
453 | 452 1
454 | 453 0
455 | 454 0
456 | 455 1
457 | 456 2
458 | 457 2
459 | 458 2
460 | 459 2
461 | 460 1
462 | 461 1
463 | 462 2
464 | 463 2
465 | 464 2
466 | 465 1
467 | 466 2
468 | 467 1
469 | 468 2
470 | 469 2
471 | 470 0
472 | 471 2
473 | 472 2
474 | 473 2
475 | 474 2
476 | 475 2
477 | 476 0
478 | 477 1
479 | 478 1
480 | 479 2
481 | 480 0
482 | 481 2
483 | 482 0
484 | 483 2
485 | 484 0
486 | 485 2
487 | 486 1
488 | 487 1
489 | 488 2
490 | 489 2
491 | 490 1
492 | 491 2
493 | 492 0
494 | 493 2
495 | 494 1
496 | 495 0
497 | 496 1
498 | 497 2
499 | 498 1
500 | 499 1
501 | 500 2
502 | 501 0
503 | 502 1
504 | 503 2
505 | 504 2
506 | 505 2
507 | 506 2
508 | 507 0
509 | 508 2
510 | 509 0
511 | 510 1
512 | 511 1
513 | 512 2
514 | 513 1
515 | 514 2
516 | 515 2
517 | 516 0
518 | 517 0
519 | 518 1
520 | 519 0
521 | 520 2
522 | 521 1
523 | 522 1
524 | 523 2
525 | 524 1
526 | 525 2
527 | 526 1
528 | 527 0
529 | 528 0
530 | 529 0
531 | 530 1
532 | 531 0
533 | 532 2
534 | 533 2
535 | 534 1
536 | 535 2
537 | 536 0
538 | 537 0
539 | 538 1
540 | 539 0
541 | 540 1
542 | 541 1
543 | 542 0
544 | 543 1
545 | 544 1
546 | 545 2
547 | 546 1
548 | 547 1
549 | 548 2
550 | 549 0
551 | 550 0
552 | 551 2
553 | 552 2
554 | 553 0
555 | 554 2
556 | 555 1
557 | 556 1
558 | 557 2
559 | 558 2
560 | 559 0
561 | 18717 2
562 | 18718 1
563 | 18719 2
564 | 18720 1
565 | 18721 1
566 | 18722 2
567 | 18723 2
568 | 18724 2
569 | 18725 2
570 | 18726 2
571 | 18727 1
572 | 18728 2
573 | 18729 1
574 | 18730 1
575 | 18731 0
576 | 18732 0
577 | 18733 1
578 | 18734 2
579 | 18735 0
580 | 18736 2
581 | 18737 0
582 | 18738 2
583 | 18739 1
584 | 18740 2
585 | 18741 2
586 | 18742 2
587 | 18743 1
588 | 18744 2
589 | 18745 1
590 | 18746 0
591 | 18747 1
592 | 18748 1
593 | 18749 0
594 | 18750 2
595 | 18751 0
596 | 18752 2
597 | 18753 2
598 | 18754 1
599 | 18755 1
600 | 18756 1
601 | 18757 2
602 | 18758 0
603 | 18759 1
604 | 18760 2
605 | 18761 1
606 | 18762 1
607 | 18763 1
608 | 18764 1
609 | 18765 1
610 | 18766 0
611 | 18767 0
612 | 18768 1
613 | 18769 2
614 | 18770 2
615 | 18771 2
616 | 18772 1
617 | 18773 2
618 | 18774 2
619 | 18775 1
620 | 18776 0
621 | 18777 2
622 | 18778 2
623 | 18779 2
624 | 18780 0
625 | 18781 0
626 | 18782 2
627 | 18783 0
628 | 18784 1
629 | 18785 2
630 | 18786 1
631 | 18787 1
632 | 18788 0
633 | 18789 1
634 | 18790 2
635 | 18791 0
636 | 18792 1
637 | 18793 2
638 | 18794 2
639 | 18795 0
640 | 18796 1
641 | 18797 1
642 | 18798 1
643 | 18799 1
644 | 18800 2
645 | 18801 2
646 | 18802 2
647 | 18803 2
648 | 18804 2
649 | 18805 2
650 | 18806 0
651 | 18807 1
652 | 18808 2
653 | 18809 1
654 | 18810 1
655 | 18811 2
656 | 18812 2
657 | 18813 1
658 | 18814 1
659 | 18815 1
660 | 18816 1
661 | 18817 1
662 | 18818 1
663 | 18819 1
664 | 18820 2
665 | 18821 0
666 | 18822 1
667 | 18823 0
668 | 18824 1
669 | 18825 1
670 | 18826 1
671 | 18827 1
672 | 18828 2
673 | 18829 0
674 | 18830 2
675 | 18831 2
676 | 18832 2
677 | 18833 2
678 | 18834 0
679 | 18835 1
680 | 18836 1
681 | 18837 1
682 | 18838 0
683 | 18839 0
684 | 18840 2
685 | 18841 2
686 | 18842 2
687 | 18843 2
688 | 18844 1
689 | 18845 0
690 | 18846 2
691 | 18847 2
692 | 18848 2
693 | 18849 2
694 | 18850 2
695 | 18851 1
696 | 18852 1
697 | 18853 1
698 | 18854 0
699 | 18855 2
700 | 18856 2
701 | 18857 2
702 | 18858 1
703 | 18859 1
704 | 18860 0
705 | 18861 1
706 | 18862 2
707 | 18863 0
708 | 18864 2
709 | 18865 2
710 | 18866 1
711 | 18867 1
712 | 18868 2
713 | 18869 0
714 | 18870 0
715 | 18871 1
716 | 18872 2
717 | 18873 2
718 | 18874 2
719 | 18875 0
720 | 18876 2
721 | 18877 1
722 | 18878 1
723 | 18879 2
724 | 18880 1
725 | 18881 2
726 | 18882 2
727 | 18883 1
728 | 18884 0
729 | 18885 2
730 | 18886 0
731 | 18887 1
732 | 18888 2
733 | 18889 2
734 | 18890 0
735 | 18891 1
736 | 18892 1
737 | 18893 0
738 | 18894 2
739 | 18895 2
740 | 18896 2
741 | 18897 1
742 | 18898 1
743 | 18899 2
744 | 18900 1
745 | 18901 0
746 | 18902 2
747 | 18903 2
748 | 18904 2
749 | 18905 2
750 | 18906 2
751 | 18907 1
752 | 18908 2
753 | 18909 1
754 | 18910 2
755 | 18911 0
756 | 18912 2
757 | 18913 1
758 | 18914 2
759 | 18915 0
760 | 18916 1
761 | 18917 2
762 | 18918 2
763 | 18919 1
764 | 18920 1
765 | 18921 1
766 | 18922 1
767 | 18923 2
768 | 18924 2
769 | 18925 2
770 | 18926 1
771 | 18927 2
772 | 18928 1
773 | 18929 2
774 | 18930 2
775 | 18931 1
776 | 18932 1
777 | 18933 2
778 | 18934 2
779 | 18935 2
780 | 18936 0
781 | 18937 1
782 | 18938 2
783 | 18939 1
784 | 18940 1
785 | 18941 1
786 | 18942 1
787 | 18943 1
788 | 18944 1
789 | 18945 1
790 | 18946 1
791 | 18947 0
792 | 18948 0
793 | 18949 2
794 | 18950 0
795 | 18951 2
796 | 18952 0
797 | 18953 1
798 | 18954 1
799 | 18955 2
800 | 18956 0
801 | 18957 1
802 | 18958 2
803 | 18959 2
804 | 18960 1
805 | 18961 2
806 | 18962 2
807 | 18963 1
808 | 18964 0
809 | 18965 2
810 | 18966 2
811 | 18967 0
812 | 18968 1
813 | 18969 2
814 | 18970 2
815 | 18971 2
816 | 18972 2
817 | 18973 1
818 | 18974 1
819 | 18975 2
820 | 18976 1
821 | 18977 1
822 | 18978 2
823 | 18979 2
824 | 18980 0
825 | 18981 2
826 | 18982 0
827 | 18983 0
828 | 18984 1
829 | 18985 1
830 | 18986 1
831 | 18987 1
832 | 18988 2
833 | 18989 2
834 | 18990 2
835 | 18991 0
836 | 18992 2
837 | 18993 0
838 | 18994 1
839 | 18995 1
840 | 18996 0
841 | 18997 1
842 | 18998 1
843 | 18999 0
844 | 19000 0
845 | 19001 2
846 | 19002 2
847 | 19003 1
848 | 19004 1
849 | 19005 1
850 | 19006 1
851 | 19007 1
852 | 19008 2
853 | 19009 2
854 | 19010 1
855 | 19011 1
856 | 19012 1
857 | 19013 0
858 | 19014 2
859 | 19015 1
860 | 19016 2
861 | 19017 1
862 | 19018 1
863 | 19019 2
864 | 19020 2
865 | 19021 0
866 | 19022 2
867 | 19023 0
868 | 19024 1
869 | 19025 1
870 | 19026 2
871 | 19027 0
872 | 19028 1
873 | 19029 2
874 | 19030 2
875 | 19031 1
876 | 19032 1
877 | 19033 1
878 | 19034 2
879 | 19035 2
880 | 19036 0
881 | 19037 2
882 | 19038 1
883 | 19039 2
884 | 19040 0
885 | 19041 0
886 | 19042 1
887 | 19043 1
888 | 19044 2
889 | 19045 1
890 | 19046 1
891 | 19047 1
892 | 19048 1
893 | 19049 1
894 | 19050 2
895 | 19051 0
896 | 19052 0
897 | 19053 0
898 | 19054 1
899 | 19055 1
900 | 19056 2
901 | 19057 1
902 | 19058 2
903 | 19059 2
904 | 19060 2
905 | 19061 2
906 | 19062 1
907 | 19063 2
908 | 19064 2
909 | 19065 2
910 | 19066 1
911 | 19067 2
912 | 19068 2
913 | 19069 2
914 | 19070 1
915 | 19071 1
916 | 19072 2
917 | 19073 0
918 | 19074 1
919 | 19075 2
920 | 19076 2
921 | 19077 1
922 | 19078 2
923 | 19079 2
924 | 19080 1
925 | 19081 1
926 | 19082 1
927 | 19083 2
928 | 19084 1
929 | 19085 2
930 | 19086 2
931 | 19087 2
932 | 19088 1
933 | 19089 1
934 | 19090 1
935 | 19091 1
936 | 19092 0
937 | 19093 2
938 | 19094 2
939 | 19095 0
940 | 19096 0
941 | 19097 1
942 | 19098 2
943 | 19099 0
944 | 19100 1
945 | 19101 1
946 | 19102 1
947 | 19103 2
948 | 19104 2
949 | 19105 1
950 | 19106 1
951 | 19107 0
952 | 19108 2
953 | 19109 0
954 | 19110 2
955 | 19111 1
956 | 19112 1
957 | 19113 1
958 | 19114 1
959 | 19115 1
960 | 19116 2
961 | 19117 0
962 | 19118 0
963 | 19119 2
964 | 19120 1
965 | 19121 1
966 | 19122 0
967 | 19123 2
968 | 19124 2
969 | 19125 2
970 | 19126 1
971 | 19127 1
972 | 19128 1
973 | 19129 2
974 | 19130 1
975 | 19131 2
976 | 19132 0
977 | 19133 2
978 | 19134 0
979 | 19135 1
980 | 19136 1
981 | 19137 0
982 | 19138 1
983 | 19139 0
984 | 19140 1
985 | 19141 1
986 | 19142 1
987 | 19143 1
988 | 19144 1
989 | 19145 1
990 | 19146 2
991 | 19147 1
992 | 19148 2
993 | 19149 0
994 | 19150 1
995 | 19151 1
996 | 19152 2
997 | 19153 1
998 | 19154 1
999 | 19155 0
1000 | 19156 2
1001 | 19157 0
1002 | 19158 1
1003 | 19159 2
1004 | 19160 0
1005 | 19161 0
1006 | 19162 1
1007 | 19163 2
1008 | 19164 1
1009 | 19165 1
1010 | 19166 2
1011 | 19167 2
1012 | 19168 2
1013 | 19169 1
1014 | 19170 0
1015 | 19171 1
1016 | 19172 2
1017 | 19173 1
1018 | 19174 2
1019 | 19175 0
1020 | 19176 1
1021 | 19177 1
1022 | 19178 0
1023 | 19179 2
1024 | 19180 1
1025 | 19181 2
1026 | 19182 2
1027 | 19183 1
1028 | 19184 1
1029 | 19185 1
1030 | 19186 1
1031 | 19187 1
1032 | 19188 1
1033 | 19189 2
1034 | 19190 2
1035 | 19191 1
1036 | 19192 2
1037 | 19193 2
1038 | 19194 0
1039 | 19195 2
1040 | 19196 1
1041 | 19197 1
1042 | 19198 2
1043 | 19199 2
1044 | 19200 0
1045 | 19201 0
1046 | 19202 1
1047 | 19203 0
1048 | 19204 2
1049 | 19205 1
1050 | 19206 1
1051 | 19207 2
1052 | 19208 0
1053 | 19209 1
1054 | 19210 0
1055 | 19211 2
1056 | 19212 2
1057 | 19213 2
1058 | 19214 2
1059 | 19215 2
1060 | 19216 1
1061 | 19217 0
1062 | 19218 1
1063 | 19219 1
1064 | 19220 2
1065 | 19221 0
1066 | 19222 2
1067 | 19223 2
1068 | 19224 2
1069 | 19225 1
1070 | 19226 1
1071 | 19227 1
1072 | 19228 2
1073 | 19229 1
1074 | 19230 1
1075 | 19231 0
1076 | 19232 2
1077 | 19233 1
1078 | 19234 2
1079 | 19235 1
1080 | 19236 1
1081 | 19237 1
1082 | 19238 2
1083 | 19239 2
1084 | 19240 1
1085 | 19241 0
1086 | 19242 0
1087 | 19243 1
1088 | 19244 1
1089 | 19245 2
1090 | 19246 1
1091 | 19247 2
1092 | 19248 2
1093 | 19249 2
1094 | 19250 1
1095 | 19251 2
1096 | 19252 0
1097 | 19253 0
1098 | 19254 0
1099 | 19255 1
1100 | 19256 0
1101 | 19257 1
1102 | 19258 2
1103 | 19259 2
1104 | 19260 0
1105 | 19261 1
1106 | 19262 1
1107 | 19263 1
1108 | 19264 1
1109 | 19265 0
1110 | 19266 2
1111 | 19267 0
1112 | 19268 1
1113 | 19269 1
1114 | 19270 1
1115 | 19271 2
1116 | 19272 2
1117 | 19273 1
1118 | 19274 1
1119 | 19275 2
1120 | 19276 1
1121 | 19277 1
1122 | 19278 2
1123 | 19279 0
1124 | 19280 2
1125 | 19281 1
1126 | 19282 2
1127 | 19283 1
1128 | 19284 1
1129 | 19285 2
1130 | 19286 1
1131 | 19287 2
1132 | 19288 1
1133 | 19289 2
1134 | 19290 2
1135 | 19291 0
1136 | 19292 2
1137 | 19293 2
1138 | 19294 1
1139 | 19295 1
1140 | 19296 2
1141 | 19297 2
1142 | 19298 0
1143 | 19299 1
1144 | 19300 1
1145 | 19301 1
1146 | 19302 1
1147 | 19303 2
1148 | 19304 0
1149 | 19305 2
1150 | 19306 2
1151 | 19307 2
1152 | 19308 1
1153 | 19309 1
1154 | 19310 1
1155 | 19311 1
1156 | 19312 0
1157 | 19313 1
1158 | 19314 2
1159 | 19315 1
1160 | 19316 0
1161 | 19317 2
1162 | 19318 2
1163 | 19319 2
1164 | 19320 1
1165 | 19321 1
1166 | 19322 2
1167 | 19323 1
1168 | 19324 2
1169 | 19325 2
1170 | 19326 1
1171 | 19327 0
1172 | 19328 2
1173 | 19329 2
1174 | 19330 2
1175 | 19331 2
1176 | 19332 2
1177 | 19333 2
1178 | 19334 2
1179 | 19335 2
1180 | 19336 2
1181 | 19337 2
1182 | 19338 1
1183 | 19339 0
1184 | 19340 2
1185 | 19341 2
1186 | 19342 1
1187 | 19343 1
1188 | 19344 2
1189 | 19345 2
1190 | 19346 1
1191 | 19347 1
1192 | 19348 2
1193 | 19349 1
1194 | 19350 1
1195 | 19351 2
1196 | 19352 1
1197 | 19353 1
1198 | 19354 2
1199 | 19355 0
1200 | 19356 0
1201 | 19357 0
1202 | 19358 1
1203 | 19359 2
1204 | 19360 1
1205 | 19361 1
1206 | 19362 2
1207 | 19363 2
1208 | 19364 0
1209 | 19365 1
1210 | 19366 1
1211 | 19367 2
1212 | 19368 2
1213 | 19369 2
1214 | 19370 1
1215 | 19371 2
1216 | 19372 1
1217 | 19373 1
1218 | 19374 1
1219 | 19375 0
1220 | 19376 1
1221 | 19377 2
1222 | 19378 1
1223 | 19379 1
1224 | 19380 1
1225 | 19381 1
1226 | 19382 1
1227 | 19383 0
1228 | 19384 2
1229 | 19385 2
1230 | 19386 2
1231 | 19387 2
1232 | 19388 2
1233 | 19389 0
1234 | 19390 1
1235 | 19391 0
1236 | 19392 2
1237 | 19393 2
1238 | 19394 1
1239 | 19395 0
1240 | 19396 0
1241 | 19397 2
1242 | 19398 1
1243 | 19399 2
1244 | 19400 2
1245 | 19401 2
1246 | 19402 2
1247 | 19403 1
1248 | 19404 1
1249 | 19405 1
1250 | 19406 2
1251 | 19407 2
1252 | 19408 1
1253 | 19409 0
1254 | 19410 2
1255 | 19411 0
1256 | 19412 2
1257 | 19413 1
1258 | 19414 1
1259 | 19415 1
1260 | 19416 1
1261 | 19417 1
1262 | 19418 0
1263 | 19419 0
1264 | 19420 1
1265 | 19421 2
1266 | 19422 1
1267 | 19423 2
1268 | 19424 2
1269 | 19425 2
1270 | 19426 2
1271 | 19427 1
1272 | 19428 2
1273 | 19429 1
1274 | 19430 1
1275 | 19431 1
1276 | 19432 1
1277 | 19433 1
1278 | 19434 2
1279 | 19435 0
1280 | 19436 1
1281 | 19437 2
1282 | 19438 2
1283 | 19439 2
1284 | 19440 1
1285 | 19441 0
1286 | 19442 2
1287 | 19443 2
1288 | 19444 2
1289 | 19445 2
1290 | 19446 2
1291 | 19447 1
1292 | 19448 0
1293 | 19449 2
1294 | 19450 0
1295 | 19451 2
1296 | 19452 1
1297 | 19453 1
1298 | 19454 2
1299 | 19455 1
1300 | 19456 0
1301 | 19457 2
1302 | 19458 2
1303 | 19459 2
1304 | 19460 2
1305 | 19461 2
1306 | 19462 1
1307 | 19463 2
1308 | 19464 0
1309 | 19465 2
1310 | 19466 0
1311 | 19467 0
1312 | 19468 1
1313 | 19469 0
1314 | 19470 1
1315 | 19471 2
1316 | 19472 2
1317 | 19473 1
1318 | 19474 0
1319 | 19475 2
1320 | 19476 1
1321 | 19477 1
1322 | 19478 0
1323 | 19479 1
1324 | 19480 2
1325 | 19481 1
1326 | 19482 1
1327 | 19483 2
1328 | 19484 1
1329 | 19485 2
1330 | 19486 0
1331 | 19487 1
1332 | 19488 1
1333 | 19489 1
1334 | 19490 2
1335 | 19491 1
1336 | 19492 1
1337 | 19493 1
1338 | 19494 2
1339 | 19495 2
1340 | 19496 2
1341 | 19497 1
1342 | 19498 2
1343 | 19499 1
1344 | 19500 0
1345 | 19501 1
1346 | 19502 0
1347 | 19503 2
1348 | 19504 1
1349 | 19505 2
1350 | 19506 1
1351 | 19507 0
1352 | 19508 0
1353 | 19509 2
1354 | 19510 2
1355 | 19511 2
1356 | 19512 1
1357 | 19513 0
1358 | 19514 2
1359 | 19515 1
1360 | 19516 1
1361 | 19517 2
1362 | 19518 2
1363 | 19519 0
1364 | 19520 1
1365 | 19521 1
1366 | 19522 2
1367 | 19523 2
1368 | 19524 2
1369 | 19525 2
1370 | 19526 1
1371 | 19527 2
1372 | 19528 1
1373 | 19529 1
1374 | 19530 2
1375 | 19531 1
1376 | 19532 2
1377 | 19533 1
1378 | 19534 2
1379 | 19535 1
1380 | 19536 1
1381 | 19537 2
1382 | 19538 1
1383 | 19539 2
1384 | 19540 1
1385 | 19541 1
1386 | 19542 1
1387 | 19543 2
1388 | 19544 1
1389 | 19545 1
1390 | 19546 1
1391 | 19547 1
1392 | 19548 2
1393 | 19549 2
1394 | 19550 1
1395 | 19551 2
1396 | 19552 1
1397 | 19553 2
1398 | 19554 2
1399 | 19555 2
1400 | 19556 0
1401 | 19557 1
1402 | 19558 1
1403 | 19559 2
1404 | 19560 0
1405 | 19561 2
1406 | 19562 1
1407 | 19563 0
1408 | 19564 1
1409 | 19565 1
1410 | 19566 2
1411 | 19567 0
1412 | 19568 1
1413 | 19569 2
1414 | 19570 1
1415 | 19571 2
1416 | 19572 0
1417 | 19573 1
1418 | 19574 1
1419 | 19575 0
1420 | 19576 2
1421 | 19577 1
1422 | 19578 1
1423 | 19579 1
1424 | 19580 1
1425 | 19581 1
1426 | 19582 2
1427 | 19583 0
1428 | 19584 1
1429 | 19585 1
1430 | 19586 1
1431 | 19587 2
1432 | 19588 1
1433 | 19589 1
1434 | 19590 1
1435 | 19591 1
1436 | 19592 2
1437 | 19593 0
1438 | 19594 1
1439 | 19595 1
1440 | 19596 1
1441 | 19597 0
1442 | 19598 2
1443 | 19599 2
1444 | 19600 1
1445 | 19601 1
1446 | 19602 0
1447 | 19603 1
1448 | 19604 2
1449 | 19605 1
1450 | 19606 2
1451 | 19607 2
1452 | 19608 2
1453 | 19609 0
1454 | 19610 1
1455 | 19611 2
1456 | 19612 2
1457 | 19613 1
1458 | 19614 2
1459 | 19615 1
1460 | 19616 2
1461 | 19617 0
1462 | 19618 0
1463 | 19619 1
1464 | 19620 1
1465 | 19621 0
1466 | 19622 2
1467 | 19623 1
1468 | 19624 1
1469 | 19625 2
1470 | 19626 0
1471 | 19627 1
1472 | 19628 1
1473 | 19629 2
1474 | 19630 2
1475 | 19631 0
1476 | 19632 2
1477 | 19633 0
1478 | 19634 2
1479 | 19635 1
1480 | 19636 0
1481 | 19637 0
1482 | 19638 2
1483 | 19639 1
1484 | 19640 2
1485 | 19641 2
1486 | 19642 1
1487 | 19643 2
1488 | 19644 0
1489 | 19645 2
1490 | 19646 2
1491 | 19647 0
1492 | 19648 2
1493 | 19649 1
1494 | 19650 0
1495 | 19651 1
1496 | 19652 1
1497 | 19653 2
1498 | 19654 0
1499 | 19655 2
1500 | 19656 2
1501 | 19657 1
1502 | 19658 2
1503 | 19659 2
1504 | 19660 2
1505 | 19661 2
1506 | 19662 1
1507 | 19663 1
1508 | 19664 0
1509 | 19665 0
1510 | 19666 2
1511 | 19667 1
1512 | 19668 1
1513 | 19669 2
1514 | 19670 2
1515 | 19671 1
1516 | 19672 0
1517 | 19673 1
1518 | 19674 0
1519 | 19675 1
1520 | 19676 0
1521 | 19677 1
1522 | 19678 0
1523 | 19679 2
1524 | 19680 2
1525 | 19681 2
1526 | 19682 1
1527 | 19683 1
1528 | 19684 2
1529 | 19685 2
1530 | 19686 1
1531 | 19687 1
1532 | 19688 0
1533 | 19689 2
1534 | 19690 2
1535 | 19691 2
1536 | 19692 1
1537 | 19693 1
1538 | 19694 2
1539 | 19695 1
1540 | 19696 2
1541 | 19697 2
1542 | 19698 2
1543 | 19699 0
1544 | 19700 1
1545 | 19701 1
1546 | 19702 1
1547 | 19703 2
1548 | 19704 1
1549 | 19705 0
1550 | 19706 0
1551 | 19707 2
1552 | 19708 2
1553 | 19709 2
1554 | 19710 2
1555 | 19711 0
1556 | 19712 2
1557 | 19713 0
1558 | 19714 2
1559 | 19715 0
1560 | 19716 2
1561 |
--------------------------------------------------------------------------------
/semisupervised/data/pubmed/test.txt:
--------------------------------------------------------------------------------
1 | 18717
2 | 18718
3 | 18719
4 | 18720
5 | 18721
6 | 18722
7 | 18723
8 | 18724
9 | 18725
10 | 18726
11 | 18727
12 | 18728
13 | 18729
14 | 18730
15 | 18731
16 | 18732
17 | 18733
18 | 18734
19 | 18735
20 | 18736
21 | 18737
22 | 18738
23 | 18739
24 | 18740
25 | 18741
26 | 18742
27 | 18743
28 | 18744
29 | 18745
30 | 18746
31 | 18747
32 | 18748
33 | 18749
34 | 18750
35 | 18751
36 | 18752
37 | 18753
38 | 18754
39 | 18755
40 | 18756
41 | 18757
42 | 18758
43 | 18759
44 | 18760
45 | 18761
46 | 18762
47 | 18763
48 | 18764
49 | 18765
50 | 18766
51 | 18767
52 | 18768
53 | 18769
54 | 18770
55 | 18771
56 | 18772
57 | 18773
58 | 18774
59 | 18775
60 | 18776
61 | 18777
62 | 18778
63 | 18779
64 | 18780
65 | 18781
66 | 18782
67 | 18783
68 | 18784
69 | 18785
70 | 18786
71 | 18787
72 | 18788
73 | 18789
74 | 18790
75 | 18791
76 | 18792
77 | 18793
78 | 18794
79 | 18795
80 | 18796
81 | 18797
82 | 18798
83 | 18799
84 | 18800
85 | 18801
86 | 18802
87 | 18803
88 | 18804
89 | 18805
90 | 18806
91 | 18807
92 | 18808
93 | 18809
94 | 18810
95 | 18811
96 | 18812
97 | 18813
98 | 18814
99 | 18815
100 | 18816
101 | 18817
102 | 18818
103 | 18819
104 | 18820
105 | 18821
106 | 18822
107 | 18823
108 | 18824
109 | 18825
110 | 18826
111 | 18827
112 | 18828
113 | 18829
114 | 18830
115 | 18831
116 | 18832
117 | 18833
118 | 18834
119 | 18835
120 | 18836
121 | 18837
122 | 18838
123 | 18839
124 | 18840
125 | 18841
126 | 18842
127 | 18843
128 | 18844
129 | 18845
130 | 18846
131 | 18847
132 | 18848
133 | 18849
134 | 18850
135 | 18851
136 | 18852
137 | 18853
138 | 18854
139 | 18855
140 | 18856
141 | 18857
142 | 18858
143 | 18859
144 | 18860
145 | 18861
146 | 18862
147 | 18863
148 | 18864
149 | 18865
150 | 18866
151 | 18867
152 | 18868
153 | 18869
154 | 18870
155 | 18871
156 | 18872
157 | 18873
158 | 18874
159 | 18875
160 | 18876
161 | 18877
162 | 18878
163 | 18879
164 | 18880
165 | 18881
166 | 18882
167 | 18883
168 | 18884
169 | 18885
170 | 18886
171 | 18887
172 | 18888
173 | 18889
174 | 18890
175 | 18891
176 | 18892
177 | 18893
178 | 18894
179 | 18895
180 | 18896
181 | 18897
182 | 18898
183 | 18899
184 | 18900
185 | 18901
186 | 18902
187 | 18903
188 | 18904
189 | 18905
190 | 18906
191 | 18907
192 | 18908
193 | 18909
194 | 18910
195 | 18911
196 | 18912
197 | 18913
198 | 18914
199 | 18915
200 | 18916
201 | 18917
202 | 18918
203 | 18919
204 | 18920
205 | 18921
206 | 18922
207 | 18923
208 | 18924
209 | 18925
210 | 18926
211 | 18927
212 | 18928
213 | 18929
214 | 18930
215 | 18931
216 | 18932
217 | 18933
218 | 18934
219 | 18935
220 | 18936
221 | 18937
222 | 18938
223 | 18939
224 | 18940
225 | 18941
226 | 18942
227 | 18943
228 | 18944
229 | 18945
230 | 18946
231 | 18947
232 | 18948
233 | 18949
234 | 18950
235 | 18951
236 | 18952
237 | 18953
238 | 18954
239 | 18955
240 | 18956
241 | 18957
242 | 18958
243 | 18959
244 | 18960
245 | 18961
246 | 18962
247 | 18963
248 | 18964
249 | 18965
250 | 18966
251 | 18967
252 | 18968
253 | 18969
254 | 18970
255 | 18971
256 | 18972
257 | 18973
258 | 18974
259 | 18975
260 | 18976
261 | 18977
262 | 18978
263 | 18979
264 | 18980
265 | 18981
266 | 18982
267 | 18983
268 | 18984
269 | 18985
270 | 18986
271 | 18987
272 | 18988
273 | 18989
274 | 18990
275 | 18991
276 | 18992
277 | 18993
278 | 18994
279 | 18995
280 | 18996
281 | 18997
282 | 18998
283 | 18999
284 | 19000
285 | 19001
286 | 19002
287 | 19003
288 | 19004
289 | 19005
290 | 19006
291 | 19007
292 | 19008
293 | 19009
294 | 19010
295 | 19011
296 | 19012
297 | 19013
298 | 19014
299 | 19015
300 | 19016
301 | 19017
302 | 19018
303 | 19019
304 | 19020
305 | 19021
306 | 19022
307 | 19023
308 | 19024
309 | 19025
310 | 19026
311 | 19027
312 | 19028
313 | 19029
314 | 19030
315 | 19031
316 | 19032
317 | 19033
318 | 19034
319 | 19035
320 | 19036
321 | 19037
322 | 19038
323 | 19039
324 | 19040
325 | 19041
326 | 19042
327 | 19043
328 | 19044
329 | 19045
330 | 19046
331 | 19047
332 | 19048
333 | 19049
334 | 19050
335 | 19051
336 | 19052
337 | 19053
338 | 19054
339 | 19055
340 | 19056
341 | 19057
342 | 19058
343 | 19059
344 | 19060
345 | 19061
346 | 19062
347 | 19063
348 | 19064
349 | 19065
350 | 19066
351 | 19067
352 | 19068
353 | 19069
354 | 19070
355 | 19071
356 | 19072
357 | 19073
358 | 19074
359 | 19075
360 | 19076
361 | 19077
362 | 19078
363 | 19079
364 | 19080
365 | 19081
366 | 19082
367 | 19083
368 | 19084
369 | 19085
370 | 19086
371 | 19087
372 | 19088
373 | 19089
374 | 19090
375 | 19091
376 | 19092
377 | 19093
378 | 19094
379 | 19095
380 | 19096
381 | 19097
382 | 19098
383 | 19099
384 | 19100
385 | 19101
386 | 19102
387 | 19103
388 | 19104
389 | 19105
390 | 19106
391 | 19107
392 | 19108
393 | 19109
394 | 19110
395 | 19111
396 | 19112
397 | 19113
398 | 19114
399 | 19115
400 | 19116
401 | 19117
402 | 19118
403 | 19119
404 | 19120
405 | 19121
406 | 19122
407 | 19123
408 | 19124
409 | 19125
410 | 19126
411 | 19127
412 | 19128
413 | 19129
414 | 19130
415 | 19131
416 | 19132
417 | 19133
418 | 19134
419 | 19135
420 | 19136
421 | 19137
422 | 19138
423 | 19139
424 | 19140
425 | 19141
426 | 19142
427 | 19143
428 | 19144
429 | 19145
430 | 19146
431 | 19147
432 | 19148
433 | 19149
434 | 19150
435 | 19151
436 | 19152
437 | 19153
438 | 19154
439 | 19155
440 | 19156
441 | 19157
442 | 19158
443 | 19159
444 | 19160
445 | 19161
446 | 19162
447 | 19163
448 | 19164
449 | 19165
450 | 19166
451 | 19167
452 | 19168
453 | 19169
454 | 19170
455 | 19171
456 | 19172
457 | 19173
458 | 19174
459 | 19175
460 | 19176
461 | 19177
462 | 19178
463 | 19179
464 | 19180
465 | 19181
466 | 19182
467 | 19183
468 | 19184
469 | 19185
470 | 19186
471 | 19187
472 | 19188
473 | 19189
474 | 19190
475 | 19191
476 | 19192
477 | 19193
478 | 19194
479 | 19195
480 | 19196
481 | 19197
482 | 19198
483 | 19199
484 | 19200
485 | 19201
486 | 19202
487 | 19203
488 | 19204
489 | 19205
490 | 19206
491 | 19207
492 | 19208
493 | 19209
494 | 19210
495 | 19211
496 | 19212
497 | 19213
498 | 19214
499 | 19215
500 | 19216
501 | 19217
502 | 19218
503 | 19219
504 | 19220
505 | 19221
506 | 19222
507 | 19223
508 | 19224
509 | 19225
510 | 19226
511 | 19227
512 | 19228
513 | 19229
514 | 19230
515 | 19231
516 | 19232
517 | 19233
518 | 19234
519 | 19235
520 | 19236
521 | 19237
522 | 19238
523 | 19239
524 | 19240
525 | 19241
526 | 19242
527 | 19243
528 | 19244
529 | 19245
530 | 19246
531 | 19247
532 | 19248
533 | 19249
534 | 19250
535 | 19251
536 | 19252
537 | 19253
538 | 19254
539 | 19255
540 | 19256
541 | 19257
542 | 19258
543 | 19259
544 | 19260
545 | 19261
546 | 19262
547 | 19263
548 | 19264
549 | 19265
550 | 19266
551 | 19267
552 | 19268
553 | 19269
554 | 19270
555 | 19271
556 | 19272
557 | 19273
558 | 19274
559 | 19275
560 | 19276
561 | 19277
562 | 19278
563 | 19279
564 | 19280
565 | 19281
566 | 19282
567 | 19283
568 | 19284
569 | 19285
570 | 19286
571 | 19287
572 | 19288
573 | 19289
574 | 19290
575 | 19291
576 | 19292
577 | 19293
578 | 19294
579 | 19295
580 | 19296
581 | 19297
582 | 19298
583 | 19299
584 | 19300
585 | 19301
586 | 19302
587 | 19303
588 | 19304
589 | 19305
590 | 19306
591 | 19307
592 | 19308
593 | 19309
594 | 19310
595 | 19311
596 | 19312
597 | 19313
598 | 19314
599 | 19315
600 | 19316
601 | 19317
602 | 19318
603 | 19319
604 | 19320
605 | 19321
606 | 19322
607 | 19323
608 | 19324
609 | 19325
610 | 19326
611 | 19327
612 | 19328
613 | 19329
614 | 19330
615 | 19331
616 | 19332
617 | 19333
618 | 19334
619 | 19335
620 | 19336
621 | 19337
622 | 19338
623 | 19339
624 | 19340
625 | 19341
626 | 19342
627 | 19343
628 | 19344
629 | 19345
630 | 19346
631 | 19347
632 | 19348
633 | 19349
634 | 19350
635 | 19351
636 | 19352
637 | 19353
638 | 19354
639 | 19355
640 | 19356
641 | 19357
642 | 19358
643 | 19359
644 | 19360
645 | 19361
646 | 19362
647 | 19363
648 | 19364
649 | 19365
650 | 19366
651 | 19367
652 | 19368
653 | 19369
654 | 19370
655 | 19371
656 | 19372
657 | 19373
658 | 19374
659 | 19375
660 | 19376
661 | 19377
662 | 19378
663 | 19379
664 | 19380
665 | 19381
666 | 19382
667 | 19383
668 | 19384
669 | 19385
670 | 19386
671 | 19387
672 | 19388
673 | 19389
674 | 19390
675 | 19391
676 | 19392
677 | 19393
678 | 19394
679 | 19395
680 | 19396
681 | 19397
682 | 19398
683 | 19399
684 | 19400
685 | 19401
686 | 19402
687 | 19403
688 | 19404
689 | 19405
690 | 19406
691 | 19407
692 | 19408
693 | 19409
694 | 19410
695 | 19411
696 | 19412
697 | 19413
698 | 19414
699 | 19415
700 | 19416
701 | 19417
702 | 19418
703 | 19419
704 | 19420
705 | 19421
706 | 19422
707 | 19423
708 | 19424
709 | 19425
710 | 19426
711 | 19427
712 | 19428
713 | 19429
714 | 19430
715 | 19431
716 | 19432
717 | 19433
718 | 19434
719 | 19435
720 | 19436
721 | 19437
722 | 19438
723 | 19439
724 | 19440
725 | 19441
726 | 19442
727 | 19443
728 | 19444
729 | 19445
730 | 19446
731 | 19447
732 | 19448
733 | 19449
734 | 19450
735 | 19451
736 | 19452
737 | 19453
738 | 19454
739 | 19455
740 | 19456
741 | 19457
742 | 19458
743 | 19459
744 | 19460
745 | 19461
746 | 19462
747 | 19463
748 | 19464
749 | 19465
750 | 19466
751 | 19467
752 | 19468
753 | 19469
754 | 19470
755 | 19471
756 | 19472
757 | 19473
758 | 19474
759 | 19475
760 | 19476
761 | 19477
762 | 19478
763 | 19479
764 | 19480
765 | 19481
766 | 19482
767 | 19483
768 | 19484
769 | 19485
770 | 19486
771 | 19487
772 | 19488
773 | 19489
774 | 19490
775 | 19491
776 | 19492
777 | 19493
778 | 19494
779 | 19495
780 | 19496
781 | 19497
782 | 19498
783 | 19499
784 | 19500
785 | 19501
786 | 19502
787 | 19503
788 | 19504
789 | 19505
790 | 19506
791 | 19507
792 | 19508
793 | 19509
794 | 19510
795 | 19511
796 | 19512
797 | 19513
798 | 19514
799 | 19515
800 | 19516
801 | 19517
802 | 19518
803 | 19519
804 | 19520
805 | 19521
806 | 19522
807 | 19523
808 | 19524
809 | 19525
810 | 19526
811 | 19527
812 | 19528
813 | 19529
814 | 19530
815 | 19531
816 | 19532
817 | 19533
818 | 19534
819 | 19535
820 | 19536
821 | 19537
822 | 19538
823 | 19539
824 | 19540
825 | 19541
826 | 19542
827 | 19543
828 | 19544
829 | 19545
830 | 19546
831 | 19547
832 | 19548
833 | 19549
834 | 19550
835 | 19551
836 | 19552
837 | 19553
838 | 19554
839 | 19555
840 | 19556
841 | 19557
842 | 19558
843 | 19559
844 | 19560
845 | 19561
846 | 19562
847 | 19563
848 | 19564
849 | 19565
850 | 19566
851 | 19567
852 | 19568
853 | 19569
854 | 19570
855 | 19571
856 | 19572
857 | 19573
858 | 19574
859 | 19575
860 | 19576
861 | 19577
862 | 19578
863 | 19579
864 | 19580
865 | 19581
866 | 19582
867 | 19583
868 | 19584
869 | 19585
870 | 19586
871 | 19587
872 | 19588
873 | 19589
874 | 19590
875 | 19591
876 | 19592
877 | 19593
878 | 19594
879 | 19595
880 | 19596
881 | 19597
882 | 19598
883 | 19599
884 | 19600
885 | 19601
886 | 19602
887 | 19603
888 | 19604
889 | 19605
890 | 19606
891 | 19607
892 | 19608
893 | 19609
894 | 19610
895 | 19611
896 | 19612
897 | 19613
898 | 19614
899 | 19615
900 | 19616
901 | 19617
902 | 19618
903 | 19619
904 | 19620
905 | 19621
906 | 19622
907 | 19623
908 | 19624
909 | 19625
910 | 19626
911 | 19627
912 | 19628
913 | 19629
914 | 19630
915 | 19631
916 | 19632
917 | 19633
918 | 19634
919 | 19635
920 | 19636
921 | 19637
922 | 19638
923 | 19639
924 | 19640
925 | 19641
926 | 19642
927 | 19643
928 | 19644
929 | 19645
930 | 19646
931 | 19647
932 | 19648
933 | 19649
934 | 19650
935 | 19651
936 | 19652
937 | 19653
938 | 19654
939 | 19655
940 | 19656
941 | 19657
942 | 19658
943 | 19659
944 | 19660
945 | 19661
946 | 19662
947 | 19663
948 | 19664
949 | 19665
950 | 19666
951 | 19667
952 | 19668
953 | 19669
954 | 19670
955 | 19671
956 | 19672
957 | 19673
958 | 19674
959 | 19675
960 | 19676
961 | 19677
962 | 19678
963 | 19679
964 | 19680
965 | 19681
966 | 19682
967 | 19683
968 | 19684
969 | 19685
970 | 19686
971 | 19687
972 | 19688
973 | 19689
974 | 19690
975 | 19691
976 | 19692
977 | 19693
978 | 19694
979 | 19695
980 | 19696
981 | 19697
982 | 19698
983 | 19699
984 | 19700
985 | 19701
986 | 19702
987 | 19703
988 | 19704
989 | 19705
990 | 19706
991 | 19707
992 | 19708
993 | 19709
994 | 19710
995 | 19711
996 | 19712
997 | 19713
998 | 19714
999 | 19715
1000 | 19716
1001 |
--------------------------------------------------------------------------------
/semisupervised/data/pubmed/train.txt:
--------------------------------------------------------------------------------
1 | 0
2 | 1
3 | 2
4 | 3
5 | 4
6 | 5
7 | 6
8 | 7
9 | 8
10 | 9
11 | 10
12 | 11
13 | 12
14 | 13
15 | 14
16 | 15
17 | 16
18 | 17
19 | 18
20 | 19
21 | 20
22 | 21
23 | 22
24 | 23
25 | 24
26 | 25
27 | 26
28 | 27
29 | 28
30 | 29
31 | 30
32 | 31
33 | 32
34 | 33
35 | 34
36 | 35
37 | 36
38 | 37
39 | 38
40 | 39
41 | 40
42 | 41
43 | 42
44 | 43
45 | 44
46 | 45
47 | 46
48 | 47
49 | 48
50 | 49
51 | 50
52 | 51
53 | 52
54 | 53
55 | 54
56 | 55
57 | 56
58 | 57
59 | 58
60 | 59
61 |
--------------------------------------------------------------------------------
/unsupervised/codes/gnn.py:
--------------------------------------------------------------------------------
1 | import math
2 | import numpy as np
3 | import torch
4 | from torch import nn
5 | from torch.nn import init
6 | from torch.autograd import Variable
7 | import torch.nn.functional as F
8 | from layer import GraphConvolution
9 |
10 | class GNNq(nn.Module):
11 | def __init__(self, opt, adj):
12 | super(GNNq, self).__init__()
13 | self.opt = opt
14 | self.adj = adj
15 |
16 | opt_ = dict([('in', opt['num_feature']), ('out', opt['hidden_dim'])])
17 | self.m1 = GraphConvolution(opt_, adj)
18 |
19 | opt_ = dict([('in', opt['hidden_dim']), ('out', opt['hidden_dim'])])
20 | self.m2 = GraphConvolution(opt_, adj)
21 |
22 | self.m3 = nn.Linear(opt['hidden_dim'], opt['num_class'])
23 |
24 | if opt['cuda']:
25 | self.cuda()
26 |
27 | def reset(self):
28 | self.m1.reset_parameters()
29 | self.m2.reset_parameters()
30 |
31 | def forward(self, x):
32 | x = F.dropout(x, self.opt['input_dropout'], training=self.training)
33 | x = self.m1(x)
34 | x = F.relu(x)
35 | x = F.dropout(x, self.opt['dropout'], training=self.training)
36 | x = self.m2(x)
37 | x = F.relu(x)
38 | x = self.m3(x)
39 | return x
40 |
41 | def predict(self, x):
42 | x = F.dropout(x, self.opt['input_dropout'], training=self.training)
43 | x = self.m1(x)
44 | x = F.relu(x)
45 | x = F.dropout(x, self.opt['dropout'], training=self.training)
46 | x = self.m2(x)
47 | x = F.relu(x)
48 | return x
49 |
50 | class GNNp(nn.Module):
51 | def __init__(self, opt, adj):
52 | super(GNNp, self).__init__()
53 | self.opt = opt
54 | self.adj = adj
55 |
56 | opt_ = dict([('in', opt['num_class']), ('out', opt['hidden_dim'])])
57 | self.m1 = GraphConvolution(opt_, adj)
58 |
59 | opt_ = dict([('in', opt['hidden_dim']), ('out', opt['hidden_dim'])])
60 | self.m2 = GraphConvolution(opt_, adj)
61 |
62 | self.m3 = nn.Linear(opt['hidden_dim'], opt['num_class'])
63 |
64 | if opt['cuda']:
65 | self.cuda()
66 |
67 | def reset(self):
68 | self.m1.reset_parameters()
69 | self.m2.reset_parameters()
70 |
71 | def forward(self, x):
72 | x = F.dropout(x, self.opt['input_dropout'], training=self.training)
73 | x = self.m1(x)
74 | x = F.relu(x)
75 | x = F.dropout(x, self.opt['dropout'], training=self.training)
76 | x = self.m2(x)
77 | x = F.relu(x)
78 | x = F.dropout(x, self.opt['dropout'], training=self.training)
79 | x = self.m3(x)
80 | return x
81 |
82 | def predict(self, x):
83 | x = F.dropout(x, self.opt['input_dropout'], training=self.training)
84 | x = self.m1(x)
85 | x = F.relu(x)
86 | x = F.dropout(x, self.opt['dropout'], training=self.training)
87 | x = self.m2(x)
88 | x = F.relu(x)
89 | return x
90 |
--------------------------------------------------------------------------------
/unsupervised/codes/layer.py:
--------------------------------------------------------------------------------
1 | import math
2 | import numpy as np
3 | import torch
4 | from torch import nn
5 | from torch.nn import init
6 | from torch.autograd import Variable
7 | import torch.nn.functional as F
8 | from torch.nn.parameter import Parameter
9 |
10 | class GraphConvolution(nn.Module):
11 |
12 | def __init__(self, opt, adj):
13 | super(GraphConvolution, self).__init__()
14 | self.opt = opt
15 | self.in_size = opt['in']
16 | self.out_size = opt['out']
17 | self.adj = adj
18 | self.weight = Parameter(torch.Tensor(self.in_size, self.out_size))
19 | self.reset_parameters()
20 |
21 | def reset_parameters(self):
22 | stdv = 1. / math.sqrt(self.out_size)
23 | self.weight.data.uniform_(-stdv, stdv)
24 |
25 | def forward(self, x):
26 | m = torch.mm(x, self.weight)
27 | m = torch.spmm(self.adj, m)
28 | return m
29 |
--------------------------------------------------------------------------------
/unsupervised/codes/loader.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import math
4 | import numpy as np
5 | import torch
6 | from torch.autograd import Variable
7 |
8 | class Vocab(object):
9 |
10 | def __init__(self, file_name, cols, with_padding=False):
11 | self.itos = []
12 | self.stoi = {}
13 | self.vocab_size = 0
14 |
15 | if with_padding:
16 | string = ''
17 | self.stoi[string] = self.vocab_size
18 | self.itos.append(string)
19 | self.vocab_size += 1
20 |
21 | fi = open(file_name, 'r')
22 | for line in fi:
23 | items = line.strip().split('\t')
24 | for col in cols:
25 | item = items[col]
26 | strings = item.strip().split(' ')
27 | for string in strings:
28 | string = string.split(':')[0]
29 | if string not in self.stoi:
30 | self.stoi[string] = self.vocab_size
31 | self.itos.append(string)
32 | self.vocab_size += 1
33 | fi.close()
34 |
35 | def __len__(self):
36 | return self.vocab_size
37 |
38 | class EntityLabel(object):
39 |
40 | def __init__(self, file_name, entity, label):
41 | self.vocab_n, self.col_n = entity
42 | self.vocab_l, self.col_l = label
43 | self.itol = [-1 for k in range(self.vocab_n.vocab_size)]
44 |
45 | fi = open(file_name, 'r')
46 | for line in fi:
47 | items = line.strip().split('\t')
48 | sn, sl = items[self.col_n], items[self.col_l]
49 | n = self.vocab_n.stoi.get(sn, -1)
50 | l = self.vocab_l.stoi.get(sl, -1)
51 | if n == -1:
52 | continue
53 | self.itol[n] = l
54 | fi.close()
55 |
56 | class EntityFeature(object):
57 |
58 | def __init__(self, file_name, entity, feature):
59 | self.vocab_n, self.col_n = entity
60 | self.vocab_f, self.col_f = feature
61 | self.itof = [[] for k in range(len(self.vocab_n))]
62 | self.one_hot = []
63 |
64 | fi = open(file_name, 'r')
65 | for line in fi:
66 | items = line.strip().split('\t')
67 | sn, sf = items[self.col_n], items[self.col_f]
68 | n = self.vocab_n.stoi.get(sn, -1)
69 | if n == -1:
70 | continue
71 | for s in sf.strip().split(' '):
72 | f = self.vocab_f.stoi.get(s.split(':')[0], -1)
73 | w = float(s.split(':')[1])
74 | if f == -1:
75 | continue
76 | self.itof[n].append((f, w))
77 | fi.close()
78 |
79 | def to_one_hot(self, binary=False):
80 | self.one_hot = [[0 for j in range(len(self.vocab_f))] for i in range(len(self.vocab_n))]
81 | for k in range(len(self.vocab_n)):
82 | sm = 0
83 | for fid, wt in self.itof[k]:
84 | if binary:
85 | wt = 1.0
86 | sm += wt
87 | for fid, wt in self.itof[k]:
88 | if binary:
89 | wt = 1.0
90 | self.one_hot[k][fid] = wt / sm
91 |
92 | class Graph(object):
93 | def __init__(self, file_name, entity, weight=None):
94 | self.vocab_n, self.col_u, self.col_v = entity
95 | self.col_w = weight
96 | self.edges = []
97 |
98 | self.node_size = -1
99 |
100 | self.eid2iid = None
101 | self.iid2eid = None
102 |
103 | self.adj_w = None
104 | self.adj_t = None
105 |
106 | with open(file_name, 'r') as fi:
107 |
108 | for line in fi:
109 | items = line.strip().split('\t')
110 |
111 | su, sv = items[self.col_u], items[self.col_v]
112 | sw = items[self.col_w] if self.col_w != None else None
113 |
114 | u, v = self.vocab_n.stoi.get(su, -1), self.vocab_n.stoi.get(sv, -1)
115 | w = float(sw) if sw != None else 1
116 |
117 | if u == -1 or v == -1 or w <= 0:
118 | continue
119 |
120 | self.edges += [(u, v, w)]
121 |
122 | def get_node_size(self):
123 | return self.node_size
124 |
125 | def get_edge_size(self):
126 | return len(self.edges)
127 |
128 | def to_symmetric(self, self_link_weight=1.0):
129 | vocab = set()
130 | for u, v, w in self.edges:
131 | vocab.add(u)
132 | vocab.add(v)
133 |
134 | pair2wt = dict()
135 | for u, v, w in self.edges:
136 | pair2wt[(u, v)] = w
137 |
138 | edges_ = list()
139 | for (u, v), w in pair2wt.items():
140 | if u == v:
141 | continue
142 | w_ = pair2wt.get((v, u), -1)
143 | if w > w_:
144 | edges_ += [(u, v, w), (v, u, w)]
145 | elif w == w_:
146 | edges_ += [(u, v, w)]
147 | for k in vocab:
148 | edges_ += [(k, k, self_link_weight)]
149 |
150 | d = dict()
151 | for u, v, w in edges_:
152 | d[u] = d.get(u, 0.0) + w
153 |
154 | self.edges = [(u, v, w/math.sqrt(d[u]*d[v])) for u, v, w in edges_]
155 |
156 | def get_sparse_adjacency(self, cuda=True):
157 | shape = torch.Size([self.vocab_n.vocab_size, self.vocab_n.vocab_size])
158 |
159 | us, vs, ws = [], [], []
160 | for u, v, w in self.edges:
161 | us += [u]
162 | vs += [v]
163 | ws += [w]
164 | index = torch.LongTensor([us, vs])
165 | value = torch.Tensor(ws)
166 | if cuda:
167 | index = index.cuda()
168 | value = value.cuda()
169 | adj = torch.sparse.FloatTensor(index, value, shape)
170 | if cuda:
171 | adj = adj.cuda()
172 |
173 | return adj
174 |
--------------------------------------------------------------------------------
/unsupervised/codes/run_citeseer.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import copy
4 | import json
5 | import datetime
6 |
7 | opt = dict()
8 |
9 | opt['dataset'] = '../data/citeseer'
10 | opt['hidden_dim'] = 512
11 | opt['input_dropout'] = 0.5
12 | opt['dropout'] = 0
13 | opt['optimizer'] = 'adam'
14 | opt['lr'] = 0.1
15 | opt['decay'] = 5e-4
16 | opt['self_link_weight'] = 1.0
17 | opt['pre_epoch'] = 200
18 | opt['epoch'] = 100
19 | opt['iter'] = 2
20 | opt['use_gold'] = 0
21 | opt['draw'] = 'exp'
22 | opt['tau'] = 0.1
23 | opt['depth'] = 3
24 |
25 | def generate_command(opt):
26 | cmd = 'python3 train.py'
27 | for opt, val in opt.items():
28 | cmd += ' --' + opt + ' ' + str(val)
29 | return cmd
30 |
31 | def run(opt):
32 | opt_ = copy.deepcopy(opt)
33 | os.system(generate_command(opt_))
34 |
35 | run(opt)
36 |
37 |
--------------------------------------------------------------------------------
/unsupervised/codes/run_cora.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | import copy
4 | import json
5 | import datetime
6 |
7 | opt = dict()
8 |
9 | opt['dataset'] = '../data/cora'
10 | opt['hidden_dim'] = 512
11 | opt['input_dropout'] = 0.5
12 | opt['dropout'] = 0
13 | opt['optimizer'] = 'adam'
14 | opt['lr'] = 0.1
15 | opt['decay'] = 5e-4
16 | opt['self_link_weight'] = 1.0
17 | opt['pre_epoch'] = 200
18 | opt['epoch'] = 100
19 | opt['iter'] = 2
20 | opt['use_gold'] = 0
21 | opt['draw'] = 'smp'
22 | opt['tau'] = 0.1
23 | opt['depth'] = 3
24 |
25 | def generate_command(opt):
26 | cmd = 'python3 train.py'
27 | for opt, val in opt.items():
28 | cmd += ' --' + opt + ' ' + str(val)
29 | return cmd
30 |
31 | def run(opt):
32 | opt_ = copy.deepcopy(opt)
33 | os.system(generate_command(opt_))
34 |
35 | run(opt)
36 |
37 |
--------------------------------------------------------------------------------
/unsupervised/codes/train.py:
--------------------------------------------------------------------------------
1 | import sys
2 | import os
3 | from datetime import datetime
4 | import time
5 | import numpy as np
6 | import random
7 | import argparse
8 | from shutil import copyfile
9 | import torch
10 | import torch.nn as nn
11 | import torch.optim as optim
12 | import torch.nn.functional as F
13 |
14 | from trainer import Trainer
15 | from gnn import GNNq, GNNp
16 | import loader
17 |
18 | parser = argparse.ArgumentParser()
19 | parser.add_argument('--dataset', type=str, default='data')
20 | parser.add_argument('--save', type=str, default='/')
21 | parser.add_argument('--hidden_dim', type=int, default=16, help='Hidden dimension.')
22 | parser.add_argument('--input_dropout', type=float, default=0.5, help='Input dropout rate.')
23 | parser.add_argument('--dropout', type=float, default=0.5, help='Dropout rate.')
24 | parser.add_argument('--optimizer', type=str, default='adam', help='Optimizer.')
25 | parser.add_argument('--lr', type=float, default=0.01, help='Learning rate.')
26 | parser.add_argument('--decay', type=float, default=5e-4, help='Weight decay for optimization')
27 | parser.add_argument('--self_link_weight', type=float, default=1.0, help='Weight of self-links.')
28 | parser.add_argument('--pre_epoch', type=int, default=200, help='Number of pre-training epochs.')
29 | parser.add_argument('--epoch', type=int, default=200, help='Number of training epochs per iteration.')
30 | parser.add_argument('--iter', type=int, default=10, help='Number of training iterations.')
31 | parser.add_argument('--use_gold', type=int, default=1, help='Whether using the ground-truth label of labeled objects, 1 for using, 0 for not using.')
32 | parser.add_argument('--tau', type=float, default=1.0, help='Annealing temperature in sampling.')
33 | parser.add_argument('--draw', type=str, default='max', help='Method for drawing object labels, max for max-pooling, smp for sampling.')
34 | parser.add_argument('--depth', type=int, default=1, help='Predicting neighbors within [depth] steps.')
35 | parser.add_argument('--seed', type=int, default=1)
36 | parser.add_argument('--cuda', type=bool, default=torch.cuda.is_available())
37 | parser.add_argument('--cpu', action='store_true', help='Ignore CUDA.')
38 | args = parser.parse_args()
39 |
40 | torch.manual_seed(args.seed)
41 | np.random.seed(args.seed)
42 | random.seed(args.seed)
43 | if args.cpu:
44 | args.cuda = False
45 | elif args.cuda:
46 | torch.cuda.manual_seed(args.seed)
47 |
48 | opt = vars(args)
49 |
50 | net_file = opt['dataset'] + '/net.txt'
51 | pseudo_label_file = opt['dataset'] + '/label.txt'
52 | real_label_file = opt['dataset'] + '/label.true'
53 | feature_file = opt['dataset'] + '/feature.txt'
54 | pseudo_train_file = opt['dataset'] + '/train.txt'
55 | real_train_file = opt['dataset'] + '/train.true'
56 | dev_file = opt['dataset'] + '/dev.txt'
57 | test_file = opt['dataset'] + '/test.txt'
58 |
59 | vocab_node = loader.Vocab(net_file, [0, 1])
60 | vocab_pseudo_label = loader.Vocab(pseudo_label_file, [1])
61 | vocab_real_label = loader.Vocab(real_label_file, [1])
62 | vocab_feature = loader.Vocab(feature_file, [1])
63 |
64 | opt['num_node'] = len(vocab_node)
65 | opt['num_feature'] = len(vocab_feature)
66 | opt['num_class'] = len(vocab_pseudo_label)
67 |
68 | graph = loader.Graph(file_name=net_file, entity=[vocab_node, 0, 1])
69 | label_pseudo = loader.EntityLabel(file_name=pseudo_label_file, entity=[vocab_node, 0], label=[vocab_pseudo_label, 1])
70 | label_real = loader.EntityLabel(file_name=real_label_file, entity=[vocab_node, 0], label=[vocab_real_label, 1])
71 | feature = loader.EntityFeature(file_name=feature_file, entity=[vocab_node, 0], feature=[vocab_feature, 1])
72 | graph.to_symmetric(opt['self_link_weight'])
73 | feature.to_one_hot(binary=True)
74 | adj = graph.get_sparse_adjacency(opt['cuda'])
75 |
76 | with open(pseudo_train_file, 'r') as fi:
77 | idx_train_pseudo = [vocab_node.stoi[line.strip()] for line in fi]
78 | with open(real_train_file, 'r') as fi:
79 | idx_train_real = [vocab_node.stoi[line.strip()] for line in fi]
80 | with open(dev_file, 'r') as fi:
81 | idx_dev = [vocab_node.stoi[line.strip()] for line in fi]
82 | with open(test_file, 'r') as fi:
83 | idx_test = [vocab_node.stoi[line.strip()] for line in fi]
84 | idx_all = list(range(opt['num_node']))
85 |
86 | inputs = torch.Tensor(feature.one_hot)
87 | target_pseudo = torch.LongTensor(label_pseudo.itol)
88 | target_real = torch.LongTensor(label_real.itol)
89 | idx_train_pseudo = torch.LongTensor(idx_train_pseudo)
90 | idx_train_real = torch.LongTensor(idx_train_real)
91 | idx_dev = torch.LongTensor(idx_dev)
92 | idx_test = torch.LongTensor(idx_test)
93 | idx_all = torch.LongTensor(idx_all)
94 | inputs_q = torch.zeros(opt['num_node'], opt['num_feature'])
95 | target_q = torch.zeros(opt['num_node'], opt['num_class'])
96 | inputs_p = torch.zeros(opt['num_node'], opt['num_class'])
97 | target_p = torch.zeros(opt['num_node'], opt['num_class'])
98 |
99 | if opt['cuda']:
100 | inputs = inputs.cuda()
101 | target_pseudo = target_pseudo.cuda()
102 | target_real = target_real.cuda()
103 | idx_train_pseudo = idx_train_pseudo.cuda()
104 | idx_train_real = idx_train_real.cuda()
105 | idx_dev = idx_dev.cuda()
106 | idx_test = idx_test.cuda()
107 | idx_all = idx_all.cuda()
108 | inputs_q = inputs_q.cuda()
109 | target_q = target_q.cuda()
110 | inputs_p = inputs_p.cuda()
111 | target_p = target_p.cuda()
112 |
113 | gnnq = GNNq(opt, adj)
114 | trainer_q = Trainer(opt, gnnq)
115 |
116 | gnnp = GNNp(opt, adj)
117 | trainer_p = Trainer(opt, gnnp)
118 |
119 | def evaluate():
120 | syn = nn.Linear(opt['hidden_dim'], len(vocab_real_label))
121 | syn.cuda()
122 | gnnq.eval()
123 | data = trainer_q.model.predict(inputs).detach()
124 | lr = 0.0025
125 | op = optim.RMSprop(syn.parameters(), lr=lr)
126 | best_dev, result = 0, 0
127 | for k in range(100):
128 | logits = syn(F.dropout(data, 0.5, training=True))
129 | loss = F.cross_entropy(logits[idx_train_real], target_real[idx_train_real])
130 | op.zero_grad()
131 | loss.backward()
132 | op.step()
133 |
134 | logits = syn(F.dropout(data, 0.5, training=False))
135 |
136 | preds = torch.max(logits[idx_dev], dim=1)[1]
137 | correct = preds.eq(target_real[idx_dev]).double()
138 | accuracy_dev = correct.sum() / idx_dev.size(0)
139 |
140 | preds = torch.max(logits[idx_test], dim=1)[1]
141 | correct = preds.eq(target_real[idx_test]).double()
142 | accuracy_test = correct.sum() / idx_test.size(0)
143 |
144 | if accuracy_dev > best_dev:
145 | best_dev = accuracy_dev
146 | result = accuracy_test
147 |
148 | print('{:.3f}'.format(result * 100))
149 |
150 | return result
151 |
152 | def init_q_data():
153 | inputs_q.copy_(inputs)
154 | temp = torch.zeros(idx_train_pseudo.size(0), target_q.size(1)).type_as(target_q)
155 | temp.scatter_(1, torch.unsqueeze(target_pseudo[idx_train_pseudo], 1), 1.0)
156 | target_q[idx_train_pseudo] = temp
157 | if opt['depth'] > 0:
158 | preds = torch.Tensor(target_q.cpu()).type_as(target_q)
159 | for d in range(opt['depth']):
160 | preds = torch.mm(adj, preds) + target_q
161 | for k in range(preds.size(0)):
162 | ones = torch.ones(preds.size(1)).cuda()
163 | preds[k] = torch.where(preds[k]>0, ones, preds[k])
164 | target_q.copy_(preds)
165 |
166 | def update_p_data():
167 | preds = trainer_q.predict(inputs_q, opt['tau'])
168 | if opt['draw'] == 'exp':
169 | inputs_p.copy_(preds)
170 | target_p.copy_(preds)
171 | elif opt['draw'] == 'max':
172 | idx_lb = torch.max(preds, dim=-1)[1]
173 | inputs_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
174 | target_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
175 | elif opt['draw'] == 'smp':
176 | idx_lb = torch.multinomial(preds, 1).squeeze(1)
177 | inputs_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
178 | target_p.zero_().scatter_(1, torch.unsqueeze(idx_lb, 1), 1.0)
179 | if opt['use_gold'] == 1:
180 | temp = torch.zeros(idx_train_pseudo.size(0), target_q.size(1)).type_as(target_q)
181 | temp.scatter_(1, torch.unsqueeze(target_pseudo[idx_train_pseudo], 1), 1.0)
182 | inputs_p[idx_train_pseudo] = temp
183 | target_p[idx_train_pseudo] = temp
184 |
185 | def update_q_data():
186 | preds = trainer_p.predict(inputs_p)
187 | target_q.copy_(preds)
188 | if opt['use_gold'] == 1:
189 | temp = torch.zeros(idx_train_pseudo.size(0), target_q.size(1)).type_as(target_q)
190 | temp.scatter_(1, torch.unsqueeze(target_pseudo[idx_train_pseudo], 1), 1.0)
191 | target_q[idx_train_pseudo] = temp
192 |
193 | def pre_train(epoches):
194 | init_q_data()
195 | for epoch in range(epoches):
196 | loss = trainer_q.update_soft(inputs_q, target_q, idx_train_pseudo)
197 |
198 | def train_p(epoches):
199 | update_p_data()
200 | for epoch in range(epoches):
201 | loss = trainer_p.update_soft(inputs_p, target_p, idx_all)
202 |
203 | def train_q(epoches):
204 | update_q_data()
205 | for epoch in range(epoches):
206 | loss = trainer_q.update_soft(inputs_q, target_q, idx_all)
207 |
208 | pre_train(opt['pre_epoch'])
209 | for k in range(opt['iter']):
210 | train_p(opt['epoch'])
211 | train_q(opt['epoch'])
212 |
213 | for k in range(50):
214 | evaluate()
215 |
216 | if opt['save'] != '/':
217 | trainer_q.save(opt['save'] + '/gnnq.pt')
218 | trainer_p.save(opt['save'] + '/gnnp.pt')
219 |
--------------------------------------------------------------------------------
/unsupervised/codes/trainer.py:
--------------------------------------------------------------------------------
1 | import math
2 | import numpy as np
3 | import torch
4 | from torch import nn
5 | from torch.nn import init
6 | from torch.autograd import Variable
7 | import torch.nn.functional as F
8 | from torch.optim import Optimizer
9 |
10 | def get_optimizer(name, parameters, lr, weight_decay=0):
11 | if name == 'sgd':
12 | return torch.optim.SGD(parameters, lr=lr, weight_decay=weight_decay)
13 | elif name == 'rmsprop':
14 | return torch.optim.RMSprop(parameters, lr=lr, weight_decay=weight_decay)
15 | elif name == 'adagrad':
16 | return torch.optim.Adagrad(parameters, lr=lr, weight_decay=weight_decay)
17 | elif name == 'adam':
18 | return torch.optim.Adam(parameters, lr=lr, weight_decay=weight_decay)
19 | elif name == 'adamax':
20 | return torch.optim.Adamax(parameters, lr=lr, weight_decay=weight_decay)
21 | else:
22 | raise Exception("Unsupported optimizer: {}".format(name))
23 |
24 | def change_lr(optimizer, new_lr):
25 | for param_group in optimizer.param_groups:
26 | param_group['lr'] = new_lr
27 |
28 | class Trainer(object):
29 | def __init__(self, opt, model):
30 | self.opt = opt
31 | self.model = model
32 | self.criterion = nn.CrossEntropyLoss()
33 | self.parameters = [p for p in self.model.parameters() if p.requires_grad]
34 | if opt['cuda']:
35 | self.criterion.cuda()
36 | self.optimizer = get_optimizer(self.opt['optimizer'], self.parameters, self.opt['lr'], self.opt['decay'])
37 |
38 | def reset(self):
39 | self.model.reset()
40 | self.optimizer = get_optimizer(self.opt['optimizer'], self.parameters, self.opt['lr'], self.opt['decay'])
41 |
42 | def update(self, inputs, target, idx):
43 | if self.opt['cuda']:
44 | inputs = inputs.cuda()
45 | target = target.cuda()
46 | idx = idx.cuda()
47 |
48 | self.model.train()
49 | self.optimizer.zero_grad()
50 |
51 | logits = self.model(inputs)
52 | loss = self.criterion(logits[idx], target[idx])
53 |
54 | loss.backward()
55 | self.optimizer.step()
56 | return loss.item()
57 |
58 | def update_soft(self, inputs, target, idx):
59 | if self.opt['cuda']:
60 | inputs = inputs.cuda()
61 | target = target.cuda()
62 | idx = idx.cuda()
63 |
64 | self.model.train()
65 | self.optimizer.zero_grad()
66 |
67 | logits = self.model(inputs)
68 | logits = torch.log_softmax(logits, dim=-1)
69 | loss = -torch.mean(torch.sum(target[idx] * logits[idx], dim=-1))
70 |
71 | loss.backward()
72 | self.optimizer.step()
73 | return loss.item()
74 |
75 | def evaluate(self, inputs, target, idx):
76 | if self.opt['cuda']:
77 | inputs = inputs.cuda()
78 | target = target.cuda()
79 | idx = idx.cuda()
80 |
81 | self.model.eval()
82 |
83 | logits = self.model(inputs)
84 | loss = self.criterion(logits[idx], target[idx])
85 | preds = torch.max(logits[idx], dim=1)[1]
86 | correct = preds.eq(target[idx]).double()
87 | accuracy = correct.sum() / idx.size(0)
88 |
89 | return loss.item(), preds, accuracy.item()
90 |
91 | def predict(self, inputs, tau=1):
92 | if self.opt['cuda']:
93 | inputs = inputs.cuda()
94 |
95 | self.model.eval()
96 |
97 | logits = self.model(inputs) / tau
98 |
99 | logits = torch.softmax(logits, dim=-1).detach()
100 |
101 | return logits
102 |
103 | def save(self, filename):
104 | params = {
105 | 'model': self.model.state_dict(),
106 | 'config': self.opt,
107 | }
108 | try:
109 | torch.save(params, filename)
110 | print("model saved to {}".format(filename))
111 | except BaseException:
112 | print("[Warning: Saving failed... continuing anyway.]")
113 |
114 | def load(self, filename):
115 | try:
116 | checkpoint = torch.load(filename)
117 | except BaseException:
118 | print("Cannot load model from {}".format(filename))
119 | exit()
120 | self.model.load_state_dict(checkpoint['model'])
121 | self.opt = checkpoint['config']
122 |
--------------------------------------------------------------------------------
/unsupervised/data/citeseer/dev.txt:
--------------------------------------------------------------------------------
1 | 120
2 | 121
3 | 122
4 | 123
5 | 124
6 | 125
7 | 126
8 | 127
9 | 128
10 | 129
11 | 130
12 | 131
13 | 132
14 | 133
15 | 134
16 | 135
17 | 136
18 | 137
19 | 138
20 | 139
21 | 140
22 | 141
23 | 142
24 | 143
25 | 144
26 | 145
27 | 146
28 | 147
29 | 148
30 | 149
31 | 150
32 | 151
33 | 152
34 | 153
35 | 154
36 | 155
37 | 156
38 | 157
39 | 158
40 | 159
41 | 160
42 | 161
43 | 162
44 | 163
45 | 164
46 | 165
47 | 166
48 | 167
49 | 168
50 | 169
51 | 170
52 | 171
53 | 172
54 | 173
55 | 174
56 | 175
57 | 176
58 | 177
59 | 178
60 | 179
61 | 180
62 | 181
63 | 182
64 | 183
65 | 184
66 | 185
67 | 186
68 | 187
69 | 188
70 | 189
71 | 190
72 | 191
73 | 192
74 | 193
75 | 194
76 | 195
77 | 196
78 | 197
79 | 198
80 | 199
81 | 200
82 | 201
83 | 202
84 | 203
85 | 204
86 | 205
87 | 206
88 | 207
89 | 208
90 | 209
91 | 210
92 | 211
93 | 212
94 | 213
95 | 214
96 | 215
97 | 216
98 | 217
99 | 218
100 | 219
101 | 220
102 | 221
103 | 222
104 | 223
105 | 224
106 | 225
107 | 226
108 | 227
109 | 228
110 | 229
111 | 230
112 | 231
113 | 232
114 | 233
115 | 234
116 | 235
117 | 236
118 | 237
119 | 238
120 | 239
121 | 240
122 | 241
123 | 242
124 | 243
125 | 244
126 | 245
127 | 246
128 | 247
129 | 248
130 | 249
131 | 250
132 | 251
133 | 252
134 | 253
135 | 254
136 | 255
137 | 256
138 | 257
139 | 258
140 | 259
141 | 260
142 | 261
143 | 262
144 | 263
145 | 264
146 | 265
147 | 266
148 | 267
149 | 268
150 | 269
151 | 270
152 | 271
153 | 272
154 | 273
155 | 274
156 | 275
157 | 276
158 | 277
159 | 278
160 | 279
161 | 280
162 | 281
163 | 282
164 | 283
165 | 284
166 | 285
167 | 286
168 | 287
169 | 288
170 | 289
171 | 290
172 | 291
173 | 292
174 | 293
175 | 294
176 | 295
177 | 296
178 | 297
179 | 298
180 | 299
181 | 300
182 | 301
183 | 302
184 | 303
185 | 304
186 | 305
187 | 306
188 | 307
189 | 308
190 | 309
191 | 310
192 | 311
193 | 312
194 | 313
195 | 314
196 | 315
197 | 316
198 | 317
199 | 318
200 | 319
201 | 320
202 | 321
203 | 322
204 | 323
205 | 324
206 | 325
207 | 326
208 | 327
209 | 328
210 | 329
211 | 330
212 | 331
213 | 332
214 | 333
215 | 334
216 | 335
217 | 336
218 | 337
219 | 338
220 | 339
221 | 340
222 | 341
223 | 342
224 | 343
225 | 344
226 | 345
227 | 346
228 | 347
229 | 348
230 | 349
231 | 350
232 | 351
233 | 352
234 | 353
235 | 354
236 | 355
237 | 356
238 | 357
239 | 358
240 | 359
241 | 360
242 | 361
243 | 362
244 | 363
245 | 364
246 | 365
247 | 366
248 | 367
249 | 368
250 | 369
251 | 370
252 | 371
253 | 372
254 | 373
255 | 374
256 | 375
257 | 376
258 | 377
259 | 378
260 | 379
261 | 380
262 | 381
263 | 382
264 | 383
265 | 384
266 | 385
267 | 386
268 | 387
269 | 388
270 | 389
271 | 390
272 | 391
273 | 392
274 | 393
275 | 394
276 | 395
277 | 396
278 | 397
279 | 398
280 | 399
281 | 400
282 | 401
283 | 402
284 | 403
285 | 404
286 | 405
287 | 406
288 | 407
289 | 408
290 | 409
291 | 410
292 | 411
293 | 412
294 | 413
295 | 414
296 | 415
297 | 416
298 | 417
299 | 418
300 | 419
301 | 420
302 | 421
303 | 422
304 | 423
305 | 424
306 | 425
307 | 426
308 | 427
309 | 428
310 | 429
311 | 430
312 | 431
313 | 432
314 | 433
315 | 434
316 | 435
317 | 436
318 | 437
319 | 438
320 | 439
321 | 440
322 | 441
323 | 442
324 | 443
325 | 444
326 | 445
327 | 446
328 | 447
329 | 448
330 | 449
331 | 450
332 | 451
333 | 452
334 | 453
335 | 454
336 | 455
337 | 456
338 | 457
339 | 458
340 | 459
341 | 460
342 | 461
343 | 462
344 | 463
345 | 464
346 | 465
347 | 466
348 | 467
349 | 468
350 | 469
351 | 470
352 | 471
353 | 472
354 | 473
355 | 474
356 | 475
357 | 476
358 | 477
359 | 478
360 | 479
361 | 480
362 | 481
363 | 482
364 | 483
365 | 484
366 | 485
367 | 486
368 | 487
369 | 488
370 | 489
371 | 490
372 | 491
373 | 492
374 | 493
375 | 494
376 | 495
377 | 496
378 | 497
379 | 498
380 | 499
381 | 500
382 | 501
383 | 502
384 | 503
385 | 504
386 | 505
387 | 506
388 | 507
389 | 508
390 | 509
391 | 510
392 | 511
393 | 512
394 | 513
395 | 514
396 | 515
397 | 516
398 | 517
399 | 518
400 | 519
401 | 520
402 | 521
403 | 522
404 | 523
405 | 524
406 | 525
407 | 526
408 | 527
409 | 528
410 | 529
411 | 530
412 | 531
413 | 532
414 | 533
415 | 534
416 | 535
417 | 536
418 | 537
419 | 538
420 | 539
421 | 540
422 | 541
423 | 542
424 | 543
425 | 544
426 | 545
427 | 546
428 | 547
429 | 548
430 | 549
431 | 550
432 | 551
433 | 552
434 | 553
435 | 554
436 | 555
437 | 556
438 | 557
439 | 558
440 | 559
441 | 560
442 | 561
443 | 562
444 | 563
445 | 564
446 | 565
447 | 566
448 | 567
449 | 568
450 | 569
451 | 570
452 | 571
453 | 572
454 | 573
455 | 574
456 | 575
457 | 576
458 | 577
459 | 578
460 | 579
461 | 580
462 | 581
463 | 582
464 | 583
465 | 584
466 | 585
467 | 586
468 | 587
469 | 588
470 | 589
471 | 590
472 | 591
473 | 592
474 | 593
475 | 594
476 | 595
477 | 596
478 | 597
479 | 598
480 | 599
481 | 600
482 | 601
483 | 602
484 | 603
485 | 604
486 | 605
487 | 606
488 | 607
489 | 608
490 | 609
491 | 610
492 | 611
493 | 612
494 | 613
495 | 614
496 | 615
497 | 616
498 | 617
499 | 618
500 | 619
501 |
--------------------------------------------------------------------------------
/unsupervised/data/citeseer/label.true:
--------------------------------------------------------------------------------
1 | 0 3
2 | 1 1
3 | 2 5
4 | 3 5
5 | 4 3
6 | 5 1
7 | 6 3
8 | 7 0
9 | 8 3
10 | 9 5
11 | 10 2
12 | 11 4
13 | 12 2
14 | 13 1
15 | 14 2
16 | 15 3
17 | 16 2
18 | 17 4
19 | 18 4
20 | 19 0
21 | 20 1
22 | 21 5
23 | 22 5
24 | 23 3
25 | 24 5
26 | 25 2
27 | 26 5
28 | 27 2
29 | 28 4
30 | 29 2
31 | 30 2
32 | 31 2
33 | 32 4
34 | 33 5
35 | 34 2
36 | 35 3
37 | 36 4
38 | 37 5
39 | 38 3
40 | 39 3
41 | 40 2
42 | 41 1
43 | 42 2
44 | 43 1
45 | 44 5
46 | 45 1
47 | 46 1
48 | 47 4
49 | 48 2
50 | 49 3
51 | 50 3
52 | 51 2
53 | 52 5
54 | 53 2
55 | 54 5
56 | 55 1
57 | 56 4
58 | 57 1
59 | 58 4
60 | 59 2
61 | 60 2
62 | 61 3
63 | 62 4
64 | 63 5
65 | 64 5
66 | 65 1
67 | 66 3
68 | 67 3
69 | 68 4
70 | 69 2
71 | 70 4
72 | 71 1
73 | 72 1
74 | 73 5
75 | 74 0
76 | 75 2
77 | 76 0
78 | 77 3
79 | 78 5
80 | 79 2
81 | 80 4
82 | 81 1
83 | 82 1
84 | 83 4
85 | 84 4
86 | 85 0
87 | 86 4
88 | 87 4
89 | 88 5
90 | 89 3
91 | 90 5
92 | 91 5
93 | 92 4
94 | 93 5
95 | 94 3
96 | 95 1
97 | 96 4
98 | 97 4
99 | 98 3
100 | 99 1
101 | 100 3
102 | 101 0
103 | 102 1
104 | 103 1
105 | 104 1
106 | 105 3
107 | 106 0
108 | 107 0
109 | 108 0
110 | 109 0
111 | 110 0
112 | 111 0
113 | 112 0
114 | 113 0
115 | 114 0
116 | 115 0
117 | 116 0
118 | 117 0
119 | 118 0
120 | 119 0
121 | 120 3
122 | 121 1
123 | 122 2
124 | 123 2
125 | 124 2
126 | 125 2
127 | 126 0
128 | 127 2
129 | 128 0
130 | 129 0
131 | 130 4
132 | 131 3
133 | 132 1
134 | 133 4
135 | 134 3
136 | 135 3
137 | 136 3
138 | 137 2
139 | 138 1
140 | 139 5
141 | 140 1
142 | 141 2
143 | 142 4
144 | 143 2
145 | 144 2
146 | 145 1
147 | 146 2
148 | 147 2
149 | 148 3
150 | 149 1
151 | 150 1
152 | 151 1
153 | 152 2
154 | 153 2
155 | 154 2
156 | 155 3
157 | 156 5
158 | 157 2
159 | 158 1
160 | 159 4
161 | 160 0
162 | 161 2
163 | 162 2
164 | 163 3
165 | 164 3
166 | 165 2
167 | 166 3
168 | 167 5
169 | 168 5
170 | 169 2
171 | 170 3
172 | 171 4
173 | 172 3
174 | 173 4
175 | 174 3
176 | 175 5
177 | 176 4
178 | 177 3
179 | 178 4
180 | 179 3
181 | 180 2
182 | 181 2
183 | 182 4
184 | 183 3
185 | 184 2
186 | 185 5
187 | 186 3
188 | 187 3
189 | 188 5
190 | 189 3
191 | 190 5
192 | 191 5
193 | 192 3
194 | 193 2
195 | 194 4
196 | 195 3
197 | 196 3
198 | 197 2
199 | 198 0
200 | 199 3
201 | 200 2
202 | 201 0
203 | 202 3
204 | 203 4
205 | 204 0
206 | 205 4
207 | 206 2
208 | 207 1
209 | 208 1
210 | 209 1
211 | 210 1
212 | 211 1
213 | 212 4
214 | 213 2
215 | 214 5
216 | 215 4
217 | 216 1
218 | 217 3
219 | 218 1
220 | 219 3
221 | 220 2
222 | 221 1
223 | 222 5
224 | 223 3
225 | 224 2
226 | 225 5
227 | 226 4
228 | 227 5
229 | 228 4
230 | 229 2
231 | 230 5
232 | 231 2
233 | 232 5
234 | 233 3
235 | 234 4
236 | 235 2
237 | 236 5
238 | 237 1
239 | 238 2
240 | 239 1
241 | 240 1
242 | 241 3
243 | 242 2
244 | 243 2
245 | 244 5
246 | 245 3
247 | 246 2
248 | 247 0
249 | 248 1
250 | 249 5
251 | 250 3
252 | 251 0
253 | 252 5
254 | 253 5
255 | 254 5
256 | 255 3
257 | 256 2
258 | 257 0
259 | 258 2
260 | 259 4
261 | 260 3
262 | 261 3
263 | 262 0
264 | 263 2
265 | 264 3
266 | 265 4
267 | 266 5
268 | 267 2
269 | 268 3
270 | 269 1
271 | 270 1
272 | 271 1
273 | 272 4
274 | 273 3
275 | 274 5
276 | 275 3
277 | 276 0
278 | 277 3
279 | 278 3
280 | 279 3
281 | 280 3
282 | 281 1
283 | 282 1
284 | 283 4
285 | 284 4
286 | 285 4
287 | 286 3
288 | 287 1
289 | 288 3
290 | 289 2
291 | 290 3
292 | 291 5
293 | 292 1
294 | 293 4
295 | 294 4
296 | 295 2
297 | 296 2
298 | 297 1
299 | 298 2
300 | 299 2
301 | 300 4
302 | 301 4
303 | 302 2
304 | 303 2
305 | 304 4
306 | 305 5
307 | 306 3
308 | 307 2
309 | 308 5
310 | 309 3
311 | 310 3
312 | 311 2
313 | 312 1
314 | 313 3
315 | 314 2
316 | 315 1
317 | 316 4
318 | 317 4
319 | 318 1
320 | 319 4
321 | 320 1
322 | 321 2
323 | 322 2
324 | 323 5
325 | 324 5
326 | 325 5
327 | 326 0
328 | 327 3
329 | 328 1
330 | 329 1
331 | 330 5
332 | 331 5
333 | 332 4
334 | 333 4
335 | 334 0
336 | 335 1
337 | 336 3
338 | 337 3
339 | 338 5
340 | 339 4
341 | 340 2
342 | 341 0
343 | 342 4
344 | 343 3
345 | 344 5
346 | 345 3
347 | 346 2
348 | 347 2
349 | 348 1
350 | 349 5
351 | 350 2
352 | 351 2
353 | 352 5
354 | 353 3
355 | 354 5
356 | 355 1
357 | 356 3
358 | 357 3
359 | 358 1
360 | 359 4
361 | 360 0
362 | 361 2
363 | 362 3
364 | 363 2
365 | 364 1
366 | 365 2
367 | 366 2
368 | 367 1
369 | 368 5
370 | 369 2
371 | 370 1
372 | 371 4
373 | 372 5
374 | 373 2
375 | 374 5
376 | 375 0
377 | 376 4
378 | 377 2
379 | 378 5
380 | 379 4
381 | 380 5
382 | 381 1
383 | 382 3
384 | 383 4
385 | 384 5
386 | 385 4
387 | 386 3
388 | 387 5
389 | 388 2
390 | 389 0
391 | 390 3
392 | 391 4
393 | 392 4
394 | 393 4
395 | 394 2
396 | 395 2
397 | 396 2
398 | 397 4
399 | 398 1
400 | 399 0
401 | 400 3
402 | 401 3
403 | 402 3
404 | 403 1
405 | 404 1
406 | 405 4
407 | 406 2
408 | 407 3
409 | 408 1
410 | 409 1
411 | 410 5
412 | 411 4
413 | 412 4
414 | 413 3
415 | 414 2
416 | 415 1
417 | 416 5
418 | 417 2
419 | 418 1
420 | 419 4
421 | 420 3
422 | 421 0
423 | 422 3
424 | 423 2
425 | 424 1
426 | 425 4
427 | 426 2
428 | 427 0
429 | 428 2
430 | 429 4
431 | 430 4
432 | 431 3
433 | 432 5
434 | 433 2
435 | 434 2
436 | 435 2
437 | 436 2
438 | 437 0
439 | 438 1
440 | 439 2
441 | 440 4
442 | 441 4
443 | 442 4
444 | 443 2
445 | 444 2
446 | 445 1
447 | 446 2
448 | 447 5
449 | 448 3
450 | 449 5
451 | 450 0
452 | 451 2
453 | 452 4
454 | 453 2
455 | 454 3
456 | 455 4
457 | 456 1
458 | 457 3
459 | 458 3
460 | 459 3
461 | 460 2
462 | 461 1
463 | 462 4
464 | 463 3
465 | 464 2
466 | 465 4
467 | 466 3
468 | 467 3
469 | 468 2
470 | 469 4
471 | 470 0
472 | 471 0
473 | 472 0
474 | 473 5
475 | 474 5
476 | 475 4
477 | 476 4
478 | 477 1
479 | 478 4
480 | 479 2
481 | 480 3
482 | 481 0
483 | 482 5
484 | 483 3
485 | 484 4
486 | 485 4
487 | 486 1
488 | 487 4
489 | 488 3
490 | 489 4
491 | 490 1
492 | 491 3
493 | 492 2
494 | 493 2
495 | 494 4
496 | 495 2
497 | 496 3
498 | 497 5
499 | 498 3
500 | 499 2
501 | 500 5
502 | 501 1
503 | 502 1
504 | 503 1
505 | 504 4
506 | 505 5
507 | 506 1
508 | 507 1
509 | 508 5
510 | 509 1
511 | 510 3
512 | 511 5
513 | 512 3
514 | 513 1
515 | 514 1
516 | 515 5
517 | 516 4
518 | 517 1
519 | 518 1
520 | 519 4
521 | 520 2
522 | 521 2
523 | 522 3
524 | 523 1
525 | 524 3
526 | 525 0
527 | 526 4
528 | 527 2
529 | 528 2
530 | 529 2
531 | 530 3
532 | 531 4
533 | 532 2
534 | 533 1
535 | 534 1
536 | 535 1
537 | 536 3
538 | 537 1
539 | 538 5
540 | 539 5
541 | 540 4
542 | 541 4
543 | 542 4
544 | 543 2
545 | 544 3
546 | 545 4
547 | 546 5
548 | 547 4
549 | 548 2
550 | 549 2
551 | 550 4
552 | 551 2
553 | 552 4
554 | 553 0
555 | 554 5
556 | 555 4
557 | 556 5
558 | 557 2
559 | 558 1
560 | 559 2
561 | 560 5
562 | 561 3
563 | 562 4
564 | 563 4
565 | 564 4
566 | 565 3
567 | 566 4
568 | 567 4
569 | 568 3
570 | 569 2
571 | 570 3
572 | 571 3
573 | 572 1
574 | 573 4
575 | 574 1
576 | 575 3
577 | 576 3
578 | 577 2
579 | 578 5
580 | 579 4
581 | 580 2
582 | 581 1
583 | 582 4
584 | 583 1
585 | 584 4
586 | 585 2
587 | 586 2
588 | 587 4
589 | 588 1
590 | 589 1
591 | 590 2
592 | 591 1
593 | 592 3
594 | 593 3
595 | 594 1
596 | 595 2
597 | 596 3
598 | 597 5
599 | 598 3
600 | 599 3
601 | 600 3
602 | 601 1
603 | 602 5
604 | 603 3
605 | 604 1
606 | 605 4
607 | 606 1
608 | 607 2
609 | 608 3
610 | 609 2
611 | 610 4
612 | 611 3
613 | 612 5
614 | 613 5
615 | 614 1
616 | 615 4
617 | 616 2
618 | 617 2
619 | 618 5
620 | 619 2
621 | 2312 4
622 | 2313 5
623 | 2314 4
624 | 2315 4
625 | 2316 4
626 | 2317 1
627 | 2318 4
628 | 2319 2
629 | 2320 3
630 | 2321 3
631 | 2322 3
632 | 2323 3
633 | 2324 2
634 | 2325 3
635 | 2326 3
636 | 2327 4
637 | 2328 2
638 | 2329 0
639 | 2330 1
640 | 2331 2
641 | 2332 0
642 | 2333 3
643 | 2334 3
644 | 2335 4
645 | 2336 2
646 | 2337 4
647 | 2338 0
648 | 2339 4
649 | 2340 3
650 | 2341 3
651 | 2342 3
652 | 2343 5
653 | 2344 4
654 | 2345 5
655 | 2346 4
656 | 2347 5
657 | 2348 1
658 | 2349 1
659 | 2350 3
660 | 2351 3
661 | 2352 3
662 | 2353 3
663 | 2354 3
664 | 2355 1
665 | 2356 2
666 | 2357 3
667 | 2358 3
668 | 2359 3
669 | 2360 1
670 | 2361 2
671 | 2362 2
672 | 2363 3
673 | 2364 3
674 | 2365 1
675 | 2366 5
676 | 2367 5
677 | 2368 5
678 | 2369 3
679 | 2370 2
680 | 2371 3
681 | 2372 3
682 | 2373 3
683 | 2374 3
684 | 2375 3
685 | 2376 3
686 | 2377 3
687 | 2378 5
688 | 2379 1
689 | 2380 3
690 | 2381 1
691 | 2382 1
692 | 2383 4
693 | 2384 1
694 | 2385 3
695 | 2386 3
696 | 2387 1
697 | 2388 3
698 | 2389 3
699 | 2390 2
700 | 2391 4
701 | 2392 3
702 | 2393 3
703 | 2394 3
704 | 2395 1
705 | 2396 2
706 | 2397 2
707 | 2398 2
708 | 2399 3
709 | 2400 5
710 | 2401 2
711 | 2402 1
712 | 2403 3
713 | 2404 2
714 | 2405 2
715 | 2406 2
716 | 2408 4
717 | 2409 3
718 | 2410 3
719 | 2411 4
720 | 2412 0
721 | 2413 3
722 | 2414 1
723 | 2415 2
724 | 2416 2
725 | 2417 2
726 | 2418 2
727 | 2419 3
728 | 2420 2
729 | 2421 2
730 | 2422 2
731 | 2423 1
732 | 2424 1
733 | 2425 5
734 | 2426 2
735 | 2427 2
736 | 2428 1
737 | 2429 2
738 | 2430 4
739 | 2431 3
740 | 2432 1
741 | 2433 1
742 | 2434 3
743 | 2435 2
744 | 2436 3
745 | 2437 4
746 | 2438 3
747 | 2439 3
748 | 2440 4
749 | 2441 4
750 | 2442 3
751 | 2443 2
752 | 2444 2
753 | 2445 1
754 | 2446 3
755 | 2447 4
756 | 2448 4
757 | 2449 4
758 | 2450 4
759 | 2451 4
760 | 2452 4
761 | 2453 5
762 | 2454 0
763 | 2455 3
764 | 2456 1
765 | 2457 1
766 | 2458 3
767 | 2459 1
768 | 2460 3
769 | 2461 1
770 | 2462 3
771 | 2463 4
772 | 2464 4
773 | 2465 3
774 | 2466 2
775 | 2467 3
776 | 2468 5
777 | 2469 3
778 | 2470 3
779 | 2471 3
780 | 2472 4
781 | 2473 2
782 | 2474 2
783 | 2475 2
784 | 2476 5
785 | 2477 3
786 | 2478 1
787 | 2479 0
788 | 2480 3
789 | 2481 2
790 | 2482 5
791 | 2483 2
792 | 2484 3
793 | 2485 2
794 | 2486 4
795 | 2487 2
796 | 2488 2
797 | 2490 2
798 | 2491 0
799 | 2492 5
800 | 2493 1
801 | 2494 3
802 | 2495 4
803 | 2496 4
804 | 2497 4
805 | 2498 1
806 | 2499 1
807 | 2500 5
808 | 2501 1
809 | 2502 2
810 | 2503 0
811 | 2504 1
812 | 2505 0
813 | 2506 2
814 | 2507 2
815 | 2508 3
816 | 2509 3
817 | 2510 3
818 | 2511 3
819 | 2512 5
820 | 2513 4
821 | 2514 4
822 | 2515 3
823 | 2516 1
824 | 2517 1
825 | 2518 2
826 | 2519 1
827 | 2520 2
828 | 2521 2
829 | 2522 2
830 | 2523 2
831 | 2524 5
832 | 2525 0
833 | 2526 1
834 | 2527 2
835 | 2528 2
836 | 2529 4
837 | 2530 0
838 | 2531 4
839 | 2532 1
840 | 2533 1
841 | 2534 2
842 | 2535 3
843 | 2536 1
844 | 2537 1
845 | 2538 2
846 | 2539 3
847 | 2540 3
848 | 2541 5
849 | 2542 2
850 | 2543 5
851 | 2544 5
852 | 2545 3
853 | 2546 1
854 | 2547 0
855 | 2548 5
856 | 2549 5
857 | 2550 5
858 | 2551 5
859 | 2552 3
860 | 2554 3
861 | 2555 3
862 | 2556 0
863 | 2557 4
864 | 2558 5
865 | 2559 3
866 | 2560 4
867 | 2561 5
868 | 2562 4
869 | 2563 5
870 | 2564 2
871 | 2565 0
872 | 2566 5
873 | 2567 5
874 | 2568 5
875 | 2569 1
876 | 2570 1
877 | 2571 3
878 | 2572 1
879 | 2573 2
880 | 2574 2
881 | 2575 2
882 | 2576 3
883 | 2577 2
884 | 2578 4
885 | 2579 5
886 | 2580 3
887 | 2581 3
888 | 2582 1
889 | 2583 3
890 | 2584 1
891 | 2585 2
892 | 2586 2
893 | 2587 1
894 | 2588 3
895 | 2589 1
896 | 2590 3
897 | 2591 1
898 | 2592 2
899 | 2593 1
900 | 2594 2
901 | 2595 1
902 | 2596 2
903 | 2597 2
904 | 2598 2
905 | 2599 2
906 | 2600 5
907 | 2601 4
908 | 2602 4
909 | 2603 5
910 | 2604 0
911 | 2605 3
912 | 2606 4
913 | 2607 5
914 | 2608 4
915 | 2609 4
916 | 2610 4
917 | 2611 4
918 | 2612 4
919 | 2613 0
920 | 2614 0
921 | 2615 1
922 | 2616 4
923 | 2617 1
924 | 2618 1
925 | 2619 5
926 | 2620 0
927 | 2621 2
928 | 2622 2
929 | 2623 3
930 | 2624 3
931 | 2625 2
932 | 2626 2
933 | 2627 0
934 | 2628 0
935 | 2629 3
936 | 2630 2
937 | 2631 4
938 | 2632 1
939 | 2633 1
940 | 2634 0
941 | 2635 0
942 | 2636 1
943 | 2637 2
944 | 2638 2
945 | 2639 2
946 | 2640 2
947 | 2641 2
948 | 2642 0
949 | 2643 4
950 | 2644 0
951 | 2645 1
952 | 2646 4
953 | 2647 1
954 | 2648 1
955 | 2649 2
956 | 2650 2
957 | 2651 3
958 | 2652 3
959 | 2653 1
960 | 2654 3
961 | 2655 2
962 | 2656 4
963 | 2657 4
964 | 2658 0
965 | 2659 0
966 | 2660 3
967 | 2661 4
968 | 2662 4
969 | 2663 2
970 | 2664 2
971 | 2665 2
972 | 2666 5
973 | 2667 5
974 | 2668 2
975 | 2669 5
976 | 2670 5
977 | 2671 5
978 | 2672 5
979 | 2673 4
980 | 2674 0
981 | 2675 2
982 | 2676 2
983 | 2677 0
984 | 2678 2
985 | 2679 4
986 | 2680 5
987 | 2681 4
988 | 2683 0
989 | 2684 3
990 | 2685 3
991 | 2686 5
992 | 2687 3
993 | 2688 3
994 | 2689 4
995 | 2690 2
996 | 2691 1
997 | 2692 5
998 | 2693 5
999 | 2694 0
1000 | 2695 1
1001 | 2696 3
1002 | 2697 3
1003 | 2698 3
1004 | 2699 5
1005 | 2700 3
1006 | 2701 3
1007 | 2702 1
1008 | 2703 1
1009 | 2704 1
1010 | 2705 1
1011 | 2706 1
1012 | 2707 1
1013 | 2708 1
1014 | 2709 1
1015 | 2710 1
1016 | 2711 1
1017 | 2712 1
1018 | 2713 4
1019 | 2714 2
1020 | 2715 2
1021 | 2716 0
1022 | 2717 2
1023 | 2718 2
1024 | 2719 2
1025 | 2720 2
1026 | 2721 4
1027 | 2722 3
1028 | 2723 3
1029 | 2724 5
1030 | 2725 5
1031 | 2726 4
1032 | 2727 5
1033 | 2728 2
1034 | 2729 4
1035 | 2730 4
1036 | 2731 4
1037 | 2732 5
1038 | 2733 5
1039 | 2734 4
1040 | 2735 2
1041 | 2736 2
1042 | 2737 3
1043 | 2738 3
1044 | 2739 4
1045 | 2740 4
1046 | 2741 3
1047 | 2742 1
1048 | 2743 3
1049 | 2744 2
1050 | 2745 0
1051 | 2746 5
1052 | 2747 5
1053 | 2748 5
1054 | 2749 3
1055 | 2750 4
1056 | 2751 1
1057 | 2752 4
1058 | 2753 0
1059 | 2754 5
1060 | 2755 5
1061 | 2756 0
1062 | 2757 3
1063 | 2758 0
1064 | 2759 2
1065 | 2760 3
1066 | 2761 5
1067 | 2762 3
1068 | 2763 4
1069 | 2764 2
1070 | 2765 2
1071 | 2766 3
1072 | 2767 5
1073 | 2768 1
1074 | 2769 5
1075 | 2770 3
1076 | 2771 4
1077 | 2772 5
1078 | 2773 5
1079 | 2774 2
1080 | 2775 2
1081 | 2776 4
1082 | 2777 3
1083 | 2778 3
1084 | 2779 3
1085 | 2780 3
1086 | 2782 2
1087 | 2783 2
1088 | 2784 2
1089 | 2785 2
1090 | 2786 2
1091 | 2787 3
1092 | 2788 0
1093 | 2789 0
1094 | 2790 5
1095 | 2791 1
1096 | 2792 2
1097 | 2793 3
1098 | 2794 3
1099 | 2795 1
1100 | 2796 3
1101 | 2797 2
1102 | 2798 4
1103 | 2799 3
1104 | 2800 1
1105 | 2801 3
1106 | 2802 3
1107 | 2803 3
1108 | 2804 3
1109 | 2805 3
1110 | 2806 1
1111 | 2807 0
1112 | 2808 5
1113 | 2809 4
1114 | 2810 4
1115 | 2811 1
1116 | 2812 1
1117 | 2813 3
1118 | 2814 4
1119 | 2815 4
1120 | 2816 4
1121 | 2817 4
1122 | 2818 5
1123 | 2819 4
1124 | 2820 2
1125 | 2821 2
1126 | 2822 2
1127 | 2823 2
1128 | 2824 2
1129 | 2825 2
1130 | 2826 2
1131 | 2827 3
1132 | 2828 2
1133 | 2829 2
1134 | 2830 2
1135 | 2831 1
1136 | 2832 4
1137 | 2833 0
1138 | 2834 1
1139 | 2835 4
1140 | 2836 4
1141 | 2837 4
1142 | 2838 1
1143 | 2839 2
1144 | 2840 1
1145 | 2841 5
1146 | 2842 5
1147 | 2843 2
1148 | 2844 4
1149 | 2845 4
1150 | 2846 2
1151 | 2847 2
1152 | 2848 3
1153 | 2849 1
1154 | 2850 1
1155 | 2851 0
1156 | 2852 0
1157 | 2853 2
1158 | 2854 1
1159 | 2855 0
1160 | 2856 1
1161 | 2857 5
1162 | 2858 1
1163 | 2859 2
1164 | 2860 2
1165 | 2861 3
1166 | 2862 2
1167 | 2863 0
1168 | 2864 0
1169 | 2865 3
1170 | 2866 3
1171 | 2867 3
1172 | 2868 2
1173 | 2869 2
1174 | 2870 2
1175 | 2871 1
1176 | 2872 1
1177 | 2873 1
1178 | 2874 3
1179 | 2875 3
1180 | 2876 3
1181 | 2877 5
1182 | 2878 3
1183 | 2879 5
1184 | 2880 2
1185 | 2881 3
1186 | 2882 2
1187 | 2883 3
1188 | 2884 1
1189 | 2885 5
1190 | 2886 2
1191 | 2887 2
1192 | 2888 3
1193 | 2889 3
1194 | 2890 3
1195 | 2891 1
1196 | 2892 1
1197 | 2893 1
1198 | 2894 3
1199 | 2895 3
1200 | 2896 3
1201 | 2897 3
1202 | 2898 4
1203 | 2899 4
1204 | 2900 1
1205 | 2901 4
1206 | 2902 4
1207 | 2903 1
1208 | 2904 3
1209 | 2905 3
1210 | 2906 1
1211 | 2907 0
1212 | 2908 3
1213 | 2909 5
1214 | 2910 4
1215 | 2911 4
1216 | 2912 2
1217 | 2913 4
1218 | 2914 1
1219 | 2915 0
1220 | 2916 3
1221 | 2917 1
1222 | 2918 4
1223 | 2919 1
1224 | 2920 4
1225 | 2921 4
1226 | 2922 0
1227 | 2923 5
1228 | 2924 3
1229 | 2925 2
1230 | 2926 2
1231 | 2927 2
1232 | 2928 5
1233 | 2929 5
1234 | 2930 0
1235 | 2931 4
1236 | 2932 4
1237 | 2933 1
1238 | 2934 2
1239 | 2935 2
1240 | 2936 3
1241 | 2937 3
1242 | 2938 3
1243 | 2939 5
1244 | 2940 5
1245 | 2941 5
1246 | 2942 1
1247 | 2943 5
1248 | 2944 1
1249 | 2945 4
1250 | 2946 3
1251 | 2947 1
1252 | 2948 5
1253 | 2949 5
1254 | 2950 4
1255 | 2951 4
1256 | 2952 2
1257 | 2954 3
1258 | 2955 1
1259 | 2956 0
1260 | 2957 0
1261 | 2958 5
1262 | 2959 3
1263 | 2960 1
1264 | 2961 2
1265 | 2962 1
1266 | 2963 4
1267 | 2964 1
1268 | 2965 4
1269 | 2966 1
1270 | 2967 2
1271 | 2968 2
1272 | 2969 5
1273 | 2970 1
1274 | 2971 2
1275 | 2972 1
1276 | 2973 4
1277 | 2974 5
1278 | 2975 5
1279 | 2976 1
1280 | 2977 4
1281 | 2978 5
1282 | 2979 5
1283 | 2980 1
1284 | 2981 1
1285 | 2982 5
1286 | 2983 5
1287 | 2984 3
1288 | 2985 1
1289 | 2986 0
1290 | 2987 0
1291 | 2988 1
1292 | 2989 0
1293 | 2990 0
1294 | 2991 2
1295 | 2992 0
1296 | 2993 4
1297 | 2994 3
1298 | 2995 4
1299 | 2996 3
1300 | 2997 3
1301 | 2998 1
1302 | 2999 2
1303 | 3000 3
1304 | 3001 5
1305 | 3002 3
1306 | 3003 5
1307 | 3004 5
1308 | 3005 5
1309 | 3006 5
1310 | 3007 5
1311 | 3008 3
1312 | 3009 4
1313 | 3010 4
1314 | 3011 5
1315 | 3012 4
1316 | 3013 2
1317 | 3014 2
1318 | 3015 5
1319 | 3016 1
1320 | 3017 4
1321 | 3018 4
1322 | 3019 4
1323 | 3020 3
1324 | 3021 1
1325 | 3022 5
1326 | 3023 3
1327 | 3024 1
1328 | 3025 3
1329 | 3026 4
1330 | 3027 2
1331 | 3028 2
1332 | 3029 4
1333 | 3030 2
1334 | 3031 1
1335 | 3032 5
1336 | 3033 2
1337 | 3034 2
1338 | 3035 5
1339 | 3036 5
1340 | 3037 3
1341 | 3038 3
1342 | 3039 4
1343 | 3040 1
1344 | 3041 1
1345 | 3043 2
1346 | 3044 5
1347 | 3045 3
1348 | 3046 4
1349 | 3047 4
1350 | 3048 4
1351 | 3049 5
1352 | 3050 5
1353 | 3051 1
1354 | 3052 5
1355 | 3053 5
1356 | 3054 1
1357 | 3055 5
1358 | 3056 5
1359 | 3057 1
1360 | 3058 1
1361 | 3059 1
1362 | 3060 4
1363 | 3061 2
1364 | 3062 3
1365 | 3064 5
1366 | 3065 4
1367 | 3066 1
1368 | 3067 1
1369 | 3068 4
1370 | 3069 5
1371 | 3070 2
1372 | 3071 3
1373 | 3072 1
1374 | 3073 2
1375 | 3074 1
1376 | 3075 4
1377 | 3076 1
1378 | 3077 4
1379 | 3078 1
1380 | 3079 1
1381 | 3080 1
1382 | 3081 0
1383 | 3082 0
1384 | 3083 1
1385 | 3084 5
1386 | 3085 0
1387 | 3086 2
1388 | 3087 1
1389 | 3088 1
1390 | 3089 5
1391 | 3090 1
1392 | 3091 1
1393 | 3092 3
1394 | 3093 2
1395 | 3094 3
1396 | 3095 3
1397 | 3096 1
1398 | 3097 1
1399 | 3098 2
1400 | 3099 3
1401 | 3100 2
1402 | 3101 3
1403 | 3102 5
1404 | 3103 5
1405 | 3104 5
1406 | 3105 5
1407 | 3106 5
1408 | 3107 5
1409 | 3108 5
1410 | 3109 5
1411 | 3110 5
1412 | 3111 3
1413 | 3112 3
1414 | 3113 5
1415 | 3114 2
1416 | 3115 2
1417 | 3116 3
1418 | 3117 4
1419 | 3118 4
1420 | 3119 4
1421 | 3120 4
1422 | 3121 0
1423 | 3122 3
1424 | 3123 0
1425 | 3124 3
1426 | 3125 4
1427 | 3126 1
1428 | 3127 1
1429 | 3128 3
1430 | 3129 3
1431 | 3130 0
1432 | 3131 4
1433 | 3132 5
1434 | 3133 0
1435 | 3134 0
1436 | 3135 0
1437 | 3136 2
1438 | 3137 1
1439 | 3138 3
1440 | 3139 4
1441 | 3140 5
1442 | 3141 2
1443 | 3142 1
1444 | 3143 1
1445 | 3144 3
1446 | 3145 3
1447 | 3146 4
1448 | 3147 4
1449 | 3148 4
1450 | 3149 2
1451 | 3150 2
1452 | 3151 1
1453 | 3152 5
1454 | 3153 4
1455 | 3154 0
1456 | 3155 5
1457 | 3156 5
1458 | 3157 4
1459 | 3158 3
1460 | 3159 4
1461 | 3160 5
1462 | 3161 0
1463 | 3162 3
1464 | 3163 0
1465 | 3164 3
1466 | 3165 4
1467 | 3166 4
1468 | 3167 3
1469 | 3168 3
1470 | 3169 3
1471 | 3170 3
1472 | 3171 3
1473 | 3172 3
1474 | 3173 3
1475 | 3174 5
1476 | 3175 2
1477 | 3176 0
1478 | 3177 0
1479 | 3178 1
1480 | 3179 0
1481 | 3180 0
1482 | 3181 0
1483 | 3182 3
1484 | 3183 1
1485 | 3184 5
1486 | 3185 3
1487 | 3186 2
1488 | 3187 3
1489 | 3188 5
1490 | 3189 3
1491 | 3190 3
1492 | 3191 3
1493 | 3192 1
1494 | 3193 5
1495 | 3194 5
1496 | 3195 5
1497 | 3196 5
1498 | 3197 1
1499 | 3198 2
1500 | 3199 1
1501 | 3200 4
1502 | 3201 5
1503 | 3202 4
1504 | 3203 3
1505 | 3204 3
1506 | 3205 5
1507 | 3206 5
1508 | 3207 1
1509 | 3208 4
1510 | 3209 2
1511 | 3210 5
1512 | 3211 4
1513 | 3213 1
1514 | 3215 4
1515 | 3216 4
1516 | 3217 4
1517 | 3218 4
1518 | 3219 5
1519 | 3220 5
1520 | 3221 4
1521 | 3222 3
1522 | 3223 4
1523 | 3224 3
1524 | 3225 5
1525 | 3226 3
1526 | 3227 3
1527 | 3228 1
1528 | 3229 1
1529 | 3230 0
1530 | 3231 4
1531 | 3232 4
1532 | 3233 3
1533 | 3234 1
1534 | 3235 1
1535 | 3236 1
1536 | 3237 1
1537 | 3238 3
1538 | 3239 3
1539 | 3240 3
1540 | 3241 4
1541 | 3242 3
1542 | 3243 1
1543 | 3244 4
1544 | 3245 1
1545 | 3246 1
1546 | 3247 3
1547 | 3248 5
1548 | 3249 5
1549 | 3251 5
1550 | 3252 4
1551 | 3253 4
1552 | 3254 1
1553 | 3255 3
1554 | 3256 1
1555 | 3257 4
1556 | 3258 3
1557 | 3259 3
1558 | 3260 3
1559 | 3261 1
1560 | 3262 2
1561 | 3263 2
1562 | 3264 5
1563 | 3265 3
1564 | 3266 2
1565 | 3267 5
1566 | 3268 1
1567 | 3269 3
1568 | 3270 3
1569 | 3271 5
1570 | 3272 5
1571 | 3273 4
1572 | 3274 0
1573 | 3275 3
1574 | 3276 5
1575 | 3277 5
1576 | 3278 5
1577 | 3279 1
1578 | 3280 2
1579 | 3281 2
1580 | 3282 4
1581 | 3283 1
1582 | 3284 4
1583 | 3285 5
1584 | 3286 5
1585 | 3287 5
1586 | 3288 4
1587 | 3289 5
1588 | 3290 2
1589 | 3291 1
1590 | 3293 5
1591 | 3294 4
1592 | 3295 4
1593 | 3296 0
1594 | 3297 3
1595 | 3298 5
1596 | 3299 4
1597 | 3300 1
1598 | 3301 3
1599 | 3302 3
1600 | 3303 5
1601 | 3304 4
1602 | 3307 2
1603 | 3308 1
1604 | 3310 0
1605 | 3311 1
1606 | 3312 3
1607 | 3313 2
1608 | 3314 4
1609 | 3315 3
1610 | 3316 2
1611 | 3317 4
1612 | 3318 4
1613 | 3319 1
1614 | 3320 1
1615 | 3321 0
1616 | 3322 3
1617 | 3323 3
1618 | 3324 3
1619 | 3325 1
1620 | 3326 5
1621 |
--------------------------------------------------------------------------------
/unsupervised/data/citeseer/test.txt:
--------------------------------------------------------------------------------
1 | 2312
2 | 2313
3 | 2314
4 | 2315
5 | 2316
6 | 2317
7 | 2318
8 | 2319
9 | 2320
10 | 2321
11 | 2322
12 | 2323
13 | 2324
14 | 2325
15 | 2326
16 | 2327
17 | 2328
18 | 2329
19 | 2330
20 | 2331
21 | 2332
22 | 2333
23 | 2334
24 | 2335
25 | 2336
26 | 2337
27 | 2338
28 | 2339
29 | 2340
30 | 2341
31 | 2342
32 | 2343
33 | 2344
34 | 2345
35 | 2346
36 | 2347
37 | 2348
38 | 2349
39 | 2350
40 | 2351
41 | 2352
42 | 2353
43 | 2354
44 | 2355
45 | 2356
46 | 2357
47 | 2358
48 | 2359
49 | 2360
50 | 2361
51 | 2362
52 | 2363
53 | 2364
54 | 2365
55 | 2366
56 | 2367
57 | 2368
58 | 2369
59 | 2370
60 | 2371
61 | 2372
62 | 2373
63 | 2374
64 | 2375
65 | 2376
66 | 2377
67 | 2378
68 | 2379
69 | 2380
70 | 2381
71 | 2382
72 | 2383
73 | 2384
74 | 2385
75 | 2386
76 | 2387
77 | 2388
78 | 2389
79 | 2390
80 | 2391
81 | 2392
82 | 2393
83 | 2394
84 | 2395
85 | 2396
86 | 2397
87 | 2398
88 | 2399
89 | 2400
90 | 2401
91 | 2402
92 | 2403
93 | 2404
94 | 2405
95 | 2406
96 | 2408
97 | 2409
98 | 2410
99 | 2411
100 | 2412
101 | 2413
102 | 2414
103 | 2415
104 | 2416
105 | 2417
106 | 2418
107 | 2419
108 | 2420
109 | 2421
110 | 2422
111 | 2423
112 | 2424
113 | 2425
114 | 2426
115 | 2427
116 | 2428
117 | 2429
118 | 2430
119 | 2431
120 | 2432
121 | 2433
122 | 2434
123 | 2435
124 | 2436
125 | 2437
126 | 2438
127 | 2439
128 | 2440
129 | 2441
130 | 2442
131 | 2443
132 | 2444
133 | 2445
134 | 2446
135 | 2447
136 | 2448
137 | 2449
138 | 2450
139 | 2451
140 | 2452
141 | 2453
142 | 2454
143 | 2455
144 | 2456
145 | 2457
146 | 2458
147 | 2459
148 | 2460
149 | 2461
150 | 2462
151 | 2463
152 | 2464
153 | 2465
154 | 2466
155 | 2467
156 | 2468
157 | 2469
158 | 2470
159 | 2471
160 | 2472
161 | 2473
162 | 2474
163 | 2475
164 | 2476
165 | 2477
166 | 2478
167 | 2479
168 | 2480
169 | 2481
170 | 2482
171 | 2483
172 | 2484
173 | 2485
174 | 2486
175 | 2487
176 | 2488
177 | 2490
178 | 2491
179 | 2492
180 | 2493
181 | 2494
182 | 2495
183 | 2496
184 | 2497
185 | 2498
186 | 2499
187 | 2500
188 | 2501
189 | 2502
190 | 2503
191 | 2504
192 | 2505
193 | 2506
194 | 2507
195 | 2508
196 | 2509
197 | 2510
198 | 2511
199 | 2512
200 | 2513
201 | 2514
202 | 2515
203 | 2516
204 | 2517
205 | 2518
206 | 2519
207 | 2520
208 | 2521
209 | 2522
210 | 2523
211 | 2524
212 | 2525
213 | 2526
214 | 2527
215 | 2528
216 | 2529
217 | 2530
218 | 2531
219 | 2532
220 | 2533
221 | 2534
222 | 2535
223 | 2536
224 | 2537
225 | 2538
226 | 2539
227 | 2540
228 | 2541
229 | 2542
230 | 2543
231 | 2544
232 | 2545
233 | 2546
234 | 2547
235 | 2548
236 | 2549
237 | 2550
238 | 2551
239 | 2552
240 | 2554
241 | 2555
242 | 2556
243 | 2557
244 | 2558
245 | 2559
246 | 2560
247 | 2561
248 | 2562
249 | 2563
250 | 2564
251 | 2565
252 | 2566
253 | 2567
254 | 2568
255 | 2569
256 | 2570
257 | 2571
258 | 2572
259 | 2573
260 | 2574
261 | 2575
262 | 2576
263 | 2577
264 | 2578
265 | 2579
266 | 2580
267 | 2581
268 | 2582
269 | 2583
270 | 2584
271 | 2585
272 | 2586
273 | 2587
274 | 2588
275 | 2589
276 | 2590
277 | 2591
278 | 2592
279 | 2593
280 | 2594
281 | 2595
282 | 2596
283 | 2597
284 | 2598
285 | 2599
286 | 2600
287 | 2601
288 | 2602
289 | 2603
290 | 2604
291 | 2605
292 | 2606
293 | 2607
294 | 2608
295 | 2609
296 | 2610
297 | 2611
298 | 2612
299 | 2613
300 | 2614
301 | 2615
302 | 2616
303 | 2617
304 | 2618
305 | 2619
306 | 2620
307 | 2621
308 | 2622
309 | 2623
310 | 2624
311 | 2625
312 | 2626
313 | 2627
314 | 2628
315 | 2629
316 | 2630
317 | 2631
318 | 2632
319 | 2633
320 | 2634
321 | 2635
322 | 2636
323 | 2637
324 | 2638
325 | 2639
326 | 2640
327 | 2641
328 | 2642
329 | 2643
330 | 2644
331 | 2645
332 | 2646
333 | 2647
334 | 2648
335 | 2649
336 | 2650
337 | 2651
338 | 2652
339 | 2653
340 | 2654
341 | 2655
342 | 2656
343 | 2657
344 | 2658
345 | 2659
346 | 2660
347 | 2661
348 | 2662
349 | 2663
350 | 2664
351 | 2665
352 | 2666
353 | 2667
354 | 2668
355 | 2669
356 | 2670
357 | 2671
358 | 2672
359 | 2673
360 | 2674
361 | 2675
362 | 2676
363 | 2677
364 | 2678
365 | 2679
366 | 2680
367 | 2681
368 | 2683
369 | 2684
370 | 2685
371 | 2686
372 | 2687
373 | 2688
374 | 2689
375 | 2690
376 | 2691
377 | 2692
378 | 2693
379 | 2694
380 | 2695
381 | 2696
382 | 2697
383 | 2698
384 | 2699
385 | 2700
386 | 2701
387 | 2702
388 | 2703
389 | 2704
390 | 2705
391 | 2706
392 | 2707
393 | 2708
394 | 2709
395 | 2710
396 | 2711
397 | 2712
398 | 2713
399 | 2714
400 | 2715
401 | 2716
402 | 2717
403 | 2718
404 | 2719
405 | 2720
406 | 2721
407 | 2722
408 | 2723
409 | 2724
410 | 2725
411 | 2726
412 | 2727
413 | 2728
414 | 2729
415 | 2730
416 | 2731
417 | 2732
418 | 2733
419 | 2734
420 | 2735
421 | 2736
422 | 2737
423 | 2738
424 | 2739
425 | 2740
426 | 2741
427 | 2742
428 | 2743
429 | 2744
430 | 2745
431 | 2746
432 | 2747
433 | 2748
434 | 2749
435 | 2750
436 | 2751
437 | 2752
438 | 2753
439 | 2754
440 | 2755
441 | 2756
442 | 2757
443 | 2758
444 | 2759
445 | 2760
446 | 2761
447 | 2762
448 | 2763
449 | 2764
450 | 2765
451 | 2766
452 | 2767
453 | 2768
454 | 2769
455 | 2770
456 | 2771
457 | 2772
458 | 2773
459 | 2774
460 | 2775
461 | 2776
462 | 2777
463 | 2778
464 | 2779
465 | 2780
466 | 2782
467 | 2783
468 | 2784
469 | 2785
470 | 2786
471 | 2787
472 | 2788
473 | 2789
474 | 2790
475 | 2791
476 | 2792
477 | 2793
478 | 2794
479 | 2795
480 | 2796
481 | 2797
482 | 2798
483 | 2799
484 | 2800
485 | 2801
486 | 2802
487 | 2803
488 | 2804
489 | 2805
490 | 2806
491 | 2807
492 | 2808
493 | 2809
494 | 2810
495 | 2811
496 | 2812
497 | 2813
498 | 2814
499 | 2815
500 | 2816
501 | 2817
502 | 2818
503 | 2819
504 | 2820
505 | 2821
506 | 2822
507 | 2823
508 | 2824
509 | 2825
510 | 2826
511 | 2827
512 | 2828
513 | 2829
514 | 2830
515 | 2831
516 | 2832
517 | 2833
518 | 2834
519 | 2835
520 | 2836
521 | 2837
522 | 2838
523 | 2839
524 | 2840
525 | 2841
526 | 2842
527 | 2843
528 | 2844
529 | 2845
530 | 2846
531 | 2847
532 | 2848
533 | 2849
534 | 2850
535 | 2851
536 | 2852
537 | 2853
538 | 2854
539 | 2855
540 | 2856
541 | 2857
542 | 2858
543 | 2859
544 | 2860
545 | 2861
546 | 2862
547 | 2863
548 | 2864
549 | 2865
550 | 2866
551 | 2867
552 | 2868
553 | 2869
554 | 2870
555 | 2871
556 | 2872
557 | 2873
558 | 2874
559 | 2875
560 | 2876
561 | 2877
562 | 2878
563 | 2879
564 | 2880
565 | 2881
566 | 2882
567 | 2883
568 | 2884
569 | 2885
570 | 2886
571 | 2887
572 | 2888
573 | 2889
574 | 2890
575 | 2891
576 | 2892
577 | 2893
578 | 2894
579 | 2895
580 | 2896
581 | 2897
582 | 2898
583 | 2899
584 | 2900
585 | 2901
586 | 2902
587 | 2903
588 | 2904
589 | 2905
590 | 2906
591 | 2907
592 | 2908
593 | 2909
594 | 2910
595 | 2911
596 | 2912
597 | 2913
598 | 2914
599 | 2915
600 | 2916
601 | 2917
602 | 2918
603 | 2919
604 | 2920
605 | 2921
606 | 2922
607 | 2923
608 | 2924
609 | 2925
610 | 2926
611 | 2927
612 | 2928
613 | 2929
614 | 2930
615 | 2931
616 | 2932
617 | 2933
618 | 2934
619 | 2935
620 | 2936
621 | 2937
622 | 2938
623 | 2939
624 | 2940
625 | 2941
626 | 2942
627 | 2943
628 | 2944
629 | 2945
630 | 2946
631 | 2947
632 | 2948
633 | 2949
634 | 2950
635 | 2951
636 | 2952
637 | 2954
638 | 2955
639 | 2956
640 | 2957
641 | 2958
642 | 2959
643 | 2960
644 | 2961
645 | 2962
646 | 2963
647 | 2964
648 | 2965
649 | 2966
650 | 2967
651 | 2968
652 | 2969
653 | 2970
654 | 2971
655 | 2972
656 | 2973
657 | 2974
658 | 2975
659 | 2976
660 | 2977
661 | 2978
662 | 2979
663 | 2980
664 | 2981
665 | 2982
666 | 2983
667 | 2984
668 | 2985
669 | 2986
670 | 2987
671 | 2988
672 | 2989
673 | 2990
674 | 2991
675 | 2992
676 | 2993
677 | 2994
678 | 2995
679 | 2996
680 | 2997
681 | 2998
682 | 2999
683 | 3000
684 | 3001
685 | 3002
686 | 3003
687 | 3004
688 | 3005
689 | 3006
690 | 3007
691 | 3008
692 | 3009
693 | 3010
694 | 3011
695 | 3012
696 | 3013
697 | 3014
698 | 3015
699 | 3016
700 | 3017
701 | 3018
702 | 3019
703 | 3020
704 | 3021
705 | 3022
706 | 3023
707 | 3024
708 | 3025
709 | 3026
710 | 3027
711 | 3028
712 | 3029
713 | 3030
714 | 3031
715 | 3032
716 | 3033
717 | 3034
718 | 3035
719 | 3036
720 | 3037
721 | 3038
722 | 3039
723 | 3040
724 | 3041
725 | 3043
726 | 3044
727 | 3045
728 | 3046
729 | 3047
730 | 3048
731 | 3049
732 | 3050
733 | 3051
734 | 3052
735 | 3053
736 | 3054
737 | 3055
738 | 3056
739 | 3057
740 | 3058
741 | 3059
742 | 3060
743 | 3061
744 | 3062
745 | 3064
746 | 3065
747 | 3066
748 | 3067
749 | 3068
750 | 3069
751 | 3070
752 | 3071
753 | 3072
754 | 3073
755 | 3074
756 | 3075
757 | 3076
758 | 3077
759 | 3078
760 | 3079
761 | 3080
762 | 3081
763 | 3082
764 | 3083
765 | 3084
766 | 3085
767 | 3086
768 | 3087
769 | 3088
770 | 3089
771 | 3090
772 | 3091
773 | 3092
774 | 3093
775 | 3094
776 | 3095
777 | 3096
778 | 3097
779 | 3098
780 | 3099
781 | 3100
782 | 3101
783 | 3102
784 | 3103
785 | 3104
786 | 3105
787 | 3106
788 | 3107
789 | 3108
790 | 3109
791 | 3110
792 | 3111
793 | 3112
794 | 3113
795 | 3114
796 | 3115
797 | 3116
798 | 3117
799 | 3118
800 | 3119
801 | 3120
802 | 3121
803 | 3122
804 | 3123
805 | 3124
806 | 3125
807 | 3126
808 | 3127
809 | 3128
810 | 3129
811 | 3130
812 | 3131
813 | 3132
814 | 3133
815 | 3134
816 | 3135
817 | 3136
818 | 3137
819 | 3138
820 | 3139
821 | 3140
822 | 3141
823 | 3142
824 | 3143
825 | 3144
826 | 3145
827 | 3146
828 | 3147
829 | 3148
830 | 3149
831 | 3150
832 | 3151
833 | 3152
834 | 3153
835 | 3154
836 | 3155
837 | 3156
838 | 3157
839 | 3158
840 | 3159
841 | 3160
842 | 3161
843 | 3162
844 | 3163
845 | 3164
846 | 3165
847 | 3166
848 | 3167
849 | 3168
850 | 3169
851 | 3170
852 | 3171
853 | 3172
854 | 3173
855 | 3174
856 | 3175
857 | 3176
858 | 3177
859 | 3178
860 | 3179
861 | 3180
862 | 3181
863 | 3182
864 | 3183
865 | 3184
866 | 3185
867 | 3186
868 | 3187
869 | 3188
870 | 3189
871 | 3190
872 | 3191
873 | 3192
874 | 3193
875 | 3194
876 | 3195
877 | 3196
878 | 3197
879 | 3198
880 | 3199
881 | 3200
882 | 3201
883 | 3202
884 | 3203
885 | 3204
886 | 3205
887 | 3206
888 | 3207
889 | 3208
890 | 3209
891 | 3210
892 | 3211
893 | 3213
894 | 3215
895 | 3216
896 | 3217
897 | 3218
898 | 3219
899 | 3220
900 | 3221
901 | 3222
902 | 3223
903 | 3224
904 | 3225
905 | 3226
906 | 3227
907 | 3228
908 | 3229
909 | 3230
910 | 3231
911 | 3232
912 | 3233
913 | 3234
914 | 3235
915 | 3236
916 | 3237
917 | 3238
918 | 3239
919 | 3240
920 | 3241
921 | 3242
922 | 3243
923 | 3244
924 | 3245
925 | 3246
926 | 3247
927 | 3248
928 | 3249
929 | 3251
930 | 3252
931 | 3253
932 | 3254
933 | 3255
934 | 3256
935 | 3257
936 | 3258
937 | 3259
938 | 3260
939 | 3261
940 | 3262
941 | 3263
942 | 3264
943 | 3265
944 | 3266
945 | 3267
946 | 3268
947 | 3269
948 | 3270
949 | 3271
950 | 3272
951 | 3273
952 | 3274
953 | 3275
954 | 3276
955 | 3277
956 | 3278
957 | 3279
958 | 3280
959 | 3281
960 | 3282
961 | 3283
962 | 3284
963 | 3285
964 | 3286
965 | 3287
966 | 3288
967 | 3289
968 | 3290
969 | 3291
970 | 3293
971 | 3294
972 | 3295
973 | 3296
974 | 3297
975 | 3298
976 | 3299
977 | 3300
978 | 3301
979 | 3302
980 | 3303
981 | 3304
982 | 3307
983 | 3308
984 | 3310
985 | 3311
986 | 3312
987 | 3313
988 | 3314
989 | 3315
990 | 3316
991 | 3317
992 | 3318
993 | 3319
994 | 3320
995 | 3321
996 | 3322
997 | 3323
998 | 3324
999 | 3325
1000 | 3326
1001 |
--------------------------------------------------------------------------------
/unsupervised/data/citeseer/train.true:
--------------------------------------------------------------------------------
1 | 0
2 | 1
3 | 2
4 | 3
5 | 4
6 | 5
7 | 6
8 | 7
9 | 8
10 | 9
11 | 10
12 | 11
13 | 12
14 | 13
15 | 14
16 | 15
17 | 16
18 | 17
19 | 18
20 | 19
21 | 20
22 | 21
23 | 22
24 | 23
25 | 24
26 | 25
27 | 26
28 | 27
29 | 28
30 | 29
31 | 30
32 | 31
33 | 32
34 | 33
35 | 34
36 | 35
37 | 36
38 | 37
39 | 38
40 | 39
41 | 40
42 | 41
43 | 42
44 | 43
45 | 44
46 | 45
47 | 46
48 | 47
49 | 48
50 | 49
51 | 50
52 | 51
53 | 52
54 | 53
55 | 54
56 | 55
57 | 56
58 | 57
59 | 58
60 | 59
61 | 60
62 | 61
63 | 62
64 | 63
65 | 64
66 | 65
67 | 66
68 | 67
69 | 68
70 | 69
71 | 70
72 | 71
73 | 72
74 | 73
75 | 74
76 | 75
77 | 76
78 | 77
79 | 78
80 | 79
81 | 80
82 | 81
83 | 82
84 | 83
85 | 84
86 | 85
87 | 86
88 | 87
89 | 88
90 | 89
91 | 90
92 | 91
93 | 92
94 | 93
95 | 94
96 | 95
97 | 96
98 | 97
99 | 98
100 | 99
101 | 100
102 | 101
103 | 102
104 | 103
105 | 104
106 | 105
107 | 106
108 | 107
109 | 108
110 | 109
111 | 110
112 | 111
113 | 112
114 | 113
115 | 114
116 | 115
117 | 116
118 | 117
119 | 118
120 | 119
121 |
--------------------------------------------------------------------------------
/unsupervised/data/cora/dev.txt:
--------------------------------------------------------------------------------
1 | 140
2 | 141
3 | 142
4 | 143
5 | 144
6 | 145
7 | 146
8 | 147
9 | 148
10 | 149
11 | 150
12 | 151
13 | 152
14 | 153
15 | 154
16 | 155
17 | 156
18 | 157
19 | 158
20 | 159
21 | 160
22 | 161
23 | 162
24 | 163
25 | 164
26 | 165
27 | 166
28 | 167
29 | 168
30 | 169
31 | 170
32 | 171
33 | 172
34 | 173
35 | 174
36 | 175
37 | 176
38 | 177
39 | 178
40 | 179
41 | 180
42 | 181
43 | 182
44 | 183
45 | 184
46 | 185
47 | 186
48 | 187
49 | 188
50 | 189
51 | 190
52 | 191
53 | 192
54 | 193
55 | 194
56 | 195
57 | 196
58 | 197
59 | 198
60 | 199
61 | 200
62 | 201
63 | 202
64 | 203
65 | 204
66 | 205
67 | 206
68 | 207
69 | 208
70 | 209
71 | 210
72 | 211
73 | 212
74 | 213
75 | 214
76 | 215
77 | 216
78 | 217
79 | 218
80 | 219
81 | 220
82 | 221
83 | 222
84 | 223
85 | 224
86 | 225
87 | 226
88 | 227
89 | 228
90 | 229
91 | 230
92 | 231
93 | 232
94 | 233
95 | 234
96 | 235
97 | 236
98 | 237
99 | 238
100 | 239
101 | 240
102 | 241
103 | 242
104 | 243
105 | 244
106 | 245
107 | 246
108 | 247
109 | 248
110 | 249
111 | 250
112 | 251
113 | 252
114 | 253
115 | 254
116 | 255
117 | 256
118 | 257
119 | 258
120 | 259
121 | 260
122 | 261
123 | 262
124 | 263
125 | 264
126 | 265
127 | 266
128 | 267
129 | 268
130 | 269
131 | 270
132 | 271
133 | 272
134 | 273
135 | 274
136 | 275
137 | 276
138 | 277
139 | 278
140 | 279
141 | 280
142 | 281
143 | 282
144 | 283
145 | 284
146 | 285
147 | 286
148 | 287
149 | 288
150 | 289
151 | 290
152 | 291
153 | 292
154 | 293
155 | 294
156 | 295
157 | 296
158 | 297
159 | 298
160 | 299
161 | 300
162 | 301
163 | 302
164 | 303
165 | 304
166 | 305
167 | 306
168 | 307
169 | 308
170 | 309
171 | 310
172 | 311
173 | 312
174 | 313
175 | 314
176 | 315
177 | 316
178 | 317
179 | 318
180 | 319
181 | 320
182 | 321
183 | 322
184 | 323
185 | 324
186 | 325
187 | 326
188 | 327
189 | 328
190 | 329
191 | 330
192 | 331
193 | 332
194 | 333
195 | 334
196 | 335
197 | 336
198 | 337
199 | 338
200 | 339
201 | 340
202 | 341
203 | 342
204 | 343
205 | 344
206 | 345
207 | 346
208 | 347
209 | 348
210 | 349
211 | 350
212 | 351
213 | 352
214 | 353
215 | 354
216 | 355
217 | 356
218 | 357
219 | 358
220 | 359
221 | 360
222 | 361
223 | 362
224 | 363
225 | 364
226 | 365
227 | 366
228 | 367
229 | 368
230 | 369
231 | 370
232 | 371
233 | 372
234 | 373
235 | 374
236 | 375
237 | 376
238 | 377
239 | 378
240 | 379
241 | 380
242 | 381
243 | 382
244 | 383
245 | 384
246 | 385
247 | 386
248 | 387
249 | 388
250 | 389
251 | 390
252 | 391
253 | 392
254 | 393
255 | 394
256 | 395
257 | 396
258 | 397
259 | 398
260 | 399
261 | 400
262 | 401
263 | 402
264 | 403
265 | 404
266 | 405
267 | 406
268 | 407
269 | 408
270 | 409
271 | 410
272 | 411
273 | 412
274 | 413
275 | 414
276 | 415
277 | 416
278 | 417
279 | 418
280 | 419
281 | 420
282 | 421
283 | 422
284 | 423
285 | 424
286 | 425
287 | 426
288 | 427
289 | 428
290 | 429
291 | 430
292 | 431
293 | 432
294 | 433
295 | 434
296 | 435
297 | 436
298 | 437
299 | 438
300 | 439
301 | 440
302 | 441
303 | 442
304 | 443
305 | 444
306 | 445
307 | 446
308 | 447
309 | 448
310 | 449
311 | 450
312 | 451
313 | 452
314 | 453
315 | 454
316 | 455
317 | 456
318 | 457
319 | 458
320 | 459
321 | 460
322 | 461
323 | 462
324 | 463
325 | 464
326 | 465
327 | 466
328 | 467
329 | 468
330 | 469
331 | 470
332 | 471
333 | 472
334 | 473
335 | 474
336 | 475
337 | 476
338 | 477
339 | 478
340 | 479
341 | 480
342 | 481
343 | 482
344 | 483
345 | 484
346 | 485
347 | 486
348 | 487
349 | 488
350 | 489
351 | 490
352 | 491
353 | 492
354 | 493
355 | 494
356 | 495
357 | 496
358 | 497
359 | 498
360 | 499
361 | 500
362 | 501
363 | 502
364 | 503
365 | 504
366 | 505
367 | 506
368 | 507
369 | 508
370 | 509
371 | 510
372 | 511
373 | 512
374 | 513
375 | 514
376 | 515
377 | 516
378 | 517
379 | 518
380 | 519
381 | 520
382 | 521
383 | 522
384 | 523
385 | 524
386 | 525
387 | 526
388 | 527
389 | 528
390 | 529
391 | 530
392 | 531
393 | 532
394 | 533
395 | 534
396 | 535
397 | 536
398 | 537
399 | 538
400 | 539
401 | 540
402 | 541
403 | 542
404 | 543
405 | 544
406 | 545
407 | 546
408 | 547
409 | 548
410 | 549
411 | 550
412 | 551
413 | 552
414 | 553
415 | 554
416 | 555
417 | 556
418 | 557
419 | 558
420 | 559
421 | 560
422 | 561
423 | 562
424 | 563
425 | 564
426 | 565
427 | 566
428 | 567
429 | 568
430 | 569
431 | 570
432 | 571
433 | 572
434 | 573
435 | 574
436 | 575
437 | 576
438 | 577
439 | 578
440 | 579
441 | 580
442 | 581
443 | 582
444 | 583
445 | 584
446 | 585
447 | 586
448 | 587
449 | 588
450 | 589
451 | 590
452 | 591
453 | 592
454 | 593
455 | 594
456 | 595
457 | 596
458 | 597
459 | 598
460 | 599
461 | 600
462 | 601
463 | 602
464 | 603
465 | 604
466 | 605
467 | 606
468 | 607
469 | 608
470 | 609
471 | 610
472 | 611
473 | 612
474 | 613
475 | 614
476 | 615
477 | 616
478 | 617
479 | 618
480 | 619
481 | 620
482 | 621
483 | 622
484 | 623
485 | 624
486 | 625
487 | 626
488 | 627
489 | 628
490 | 629
491 | 630
492 | 631
493 | 632
494 | 633
495 | 634
496 | 635
497 | 636
498 | 637
499 | 638
500 | 639
501 |
--------------------------------------------------------------------------------
/unsupervised/data/cora/test.txt:
--------------------------------------------------------------------------------
1 | 1708
2 | 1709
3 | 1710
4 | 1711
5 | 1712
6 | 1713
7 | 1714
8 | 1715
9 | 1716
10 | 1717
11 | 1718
12 | 1719
13 | 1720
14 | 1721
15 | 1722
16 | 1723
17 | 1724
18 | 1725
19 | 1726
20 | 1727
21 | 1728
22 | 1729
23 | 1730
24 | 1731
25 | 1732
26 | 1733
27 | 1734
28 | 1735
29 | 1736
30 | 1737
31 | 1738
32 | 1739
33 | 1740
34 | 1741
35 | 1742
36 | 1743
37 | 1744
38 | 1745
39 | 1746
40 | 1747
41 | 1748
42 | 1749
43 | 1750
44 | 1751
45 | 1752
46 | 1753
47 | 1754
48 | 1755
49 | 1756
50 | 1757
51 | 1758
52 | 1759
53 | 1760
54 | 1761
55 | 1762
56 | 1763
57 | 1764
58 | 1765
59 | 1766
60 | 1767
61 | 1768
62 | 1769
63 | 1770
64 | 1771
65 | 1772
66 | 1773
67 | 1774
68 | 1775
69 | 1776
70 | 1777
71 | 1778
72 | 1779
73 | 1780
74 | 1781
75 | 1782
76 | 1783
77 | 1784
78 | 1785
79 | 1786
80 | 1787
81 | 1788
82 | 1789
83 | 1790
84 | 1791
85 | 1792
86 | 1793
87 | 1794
88 | 1795
89 | 1796
90 | 1797
91 | 1798
92 | 1799
93 | 1800
94 | 1801
95 | 1802
96 | 1803
97 | 1804
98 | 1805
99 | 1806
100 | 1807
101 | 1808
102 | 1809
103 | 1810
104 | 1811
105 | 1812
106 | 1813
107 | 1814
108 | 1815
109 | 1816
110 | 1817
111 | 1818
112 | 1819
113 | 1820
114 | 1821
115 | 1822
116 | 1823
117 | 1824
118 | 1825
119 | 1826
120 | 1827
121 | 1828
122 | 1829
123 | 1830
124 | 1831
125 | 1832
126 | 1833
127 | 1834
128 | 1835
129 | 1836
130 | 1837
131 | 1838
132 | 1839
133 | 1840
134 | 1841
135 | 1842
136 | 1843
137 | 1844
138 | 1845
139 | 1846
140 | 1847
141 | 1848
142 | 1849
143 | 1850
144 | 1851
145 | 1852
146 | 1853
147 | 1854
148 | 1855
149 | 1856
150 | 1857
151 | 1858
152 | 1859
153 | 1860
154 | 1861
155 | 1862
156 | 1863
157 | 1864
158 | 1865
159 | 1866
160 | 1867
161 | 1868
162 | 1869
163 | 1870
164 | 1871
165 | 1872
166 | 1873
167 | 1874
168 | 1875
169 | 1876
170 | 1877
171 | 1878
172 | 1879
173 | 1880
174 | 1881
175 | 1882
176 | 1883
177 | 1884
178 | 1885
179 | 1886
180 | 1887
181 | 1888
182 | 1889
183 | 1890
184 | 1891
185 | 1892
186 | 1893
187 | 1894
188 | 1895
189 | 1896
190 | 1897
191 | 1898
192 | 1899
193 | 1900
194 | 1901
195 | 1902
196 | 1903
197 | 1904
198 | 1905
199 | 1906
200 | 1907
201 | 1908
202 | 1909
203 | 1910
204 | 1911
205 | 1912
206 | 1913
207 | 1914
208 | 1915
209 | 1916
210 | 1917
211 | 1918
212 | 1919
213 | 1920
214 | 1921
215 | 1922
216 | 1923
217 | 1924
218 | 1925
219 | 1926
220 | 1927
221 | 1928
222 | 1929
223 | 1930
224 | 1931
225 | 1932
226 | 1933
227 | 1934
228 | 1935
229 | 1936
230 | 1937
231 | 1938
232 | 1939
233 | 1940
234 | 1941
235 | 1942
236 | 1943
237 | 1944
238 | 1945
239 | 1946
240 | 1947
241 | 1948
242 | 1949
243 | 1950
244 | 1951
245 | 1952
246 | 1953
247 | 1954
248 | 1955
249 | 1956
250 | 1957
251 | 1958
252 | 1959
253 | 1960
254 | 1961
255 | 1962
256 | 1963
257 | 1964
258 | 1965
259 | 1966
260 | 1967
261 | 1968
262 | 1969
263 | 1970
264 | 1971
265 | 1972
266 | 1973
267 | 1974
268 | 1975
269 | 1976
270 | 1977
271 | 1978
272 | 1979
273 | 1980
274 | 1981
275 | 1982
276 | 1983
277 | 1984
278 | 1985
279 | 1986
280 | 1987
281 | 1988
282 | 1989
283 | 1990
284 | 1991
285 | 1992
286 | 1993
287 | 1994
288 | 1995
289 | 1996
290 | 1997
291 | 1998
292 | 1999
293 | 2000
294 | 2001
295 | 2002
296 | 2003
297 | 2004
298 | 2005
299 | 2006
300 | 2007
301 | 2008
302 | 2009
303 | 2010
304 | 2011
305 | 2012
306 | 2013
307 | 2014
308 | 2015
309 | 2016
310 | 2017
311 | 2018
312 | 2019
313 | 2020
314 | 2021
315 | 2022
316 | 2023
317 | 2024
318 | 2025
319 | 2026
320 | 2027
321 | 2028
322 | 2029
323 | 2030
324 | 2031
325 | 2032
326 | 2033
327 | 2034
328 | 2035
329 | 2036
330 | 2037
331 | 2038
332 | 2039
333 | 2040
334 | 2041
335 | 2042
336 | 2043
337 | 2044
338 | 2045
339 | 2046
340 | 2047
341 | 2048
342 | 2049
343 | 2050
344 | 2051
345 | 2052
346 | 2053
347 | 2054
348 | 2055
349 | 2056
350 | 2057
351 | 2058
352 | 2059
353 | 2060
354 | 2061
355 | 2062
356 | 2063
357 | 2064
358 | 2065
359 | 2066
360 | 2067
361 | 2068
362 | 2069
363 | 2070
364 | 2071
365 | 2072
366 | 2073
367 | 2074
368 | 2075
369 | 2076
370 | 2077
371 | 2078
372 | 2079
373 | 2080
374 | 2081
375 | 2082
376 | 2083
377 | 2084
378 | 2085
379 | 2086
380 | 2087
381 | 2088
382 | 2089
383 | 2090
384 | 2091
385 | 2092
386 | 2093
387 | 2094
388 | 2095
389 | 2096
390 | 2097
391 | 2098
392 | 2099
393 | 2100
394 | 2101
395 | 2102
396 | 2103
397 | 2104
398 | 2105
399 | 2106
400 | 2107
401 | 2108
402 | 2109
403 | 2110
404 | 2111
405 | 2112
406 | 2113
407 | 2114
408 | 2115
409 | 2116
410 | 2117
411 | 2118
412 | 2119
413 | 2120
414 | 2121
415 | 2122
416 | 2123
417 | 2124
418 | 2125
419 | 2126
420 | 2127
421 | 2128
422 | 2129
423 | 2130
424 | 2131
425 | 2132
426 | 2133
427 | 2134
428 | 2135
429 | 2136
430 | 2137
431 | 2138
432 | 2139
433 | 2140
434 | 2141
435 | 2142
436 | 2143
437 | 2144
438 | 2145
439 | 2146
440 | 2147
441 | 2148
442 | 2149
443 | 2150
444 | 2151
445 | 2152
446 | 2153
447 | 2154
448 | 2155
449 | 2156
450 | 2157
451 | 2158
452 | 2159
453 | 2160
454 | 2161
455 | 2162
456 | 2163
457 | 2164
458 | 2165
459 | 2166
460 | 2167
461 | 2168
462 | 2169
463 | 2170
464 | 2171
465 | 2172
466 | 2173
467 | 2174
468 | 2175
469 | 2176
470 | 2177
471 | 2178
472 | 2179
473 | 2180
474 | 2181
475 | 2182
476 | 2183
477 | 2184
478 | 2185
479 | 2186
480 | 2187
481 | 2188
482 | 2189
483 | 2190
484 | 2191
485 | 2192
486 | 2193
487 | 2194
488 | 2195
489 | 2196
490 | 2197
491 | 2198
492 | 2199
493 | 2200
494 | 2201
495 | 2202
496 | 2203
497 | 2204
498 | 2205
499 | 2206
500 | 2207
501 | 2208
502 | 2209
503 | 2210
504 | 2211
505 | 2212
506 | 2213
507 | 2214
508 | 2215
509 | 2216
510 | 2217
511 | 2218
512 | 2219
513 | 2220
514 | 2221
515 | 2222
516 | 2223
517 | 2224
518 | 2225
519 | 2226
520 | 2227
521 | 2228
522 | 2229
523 | 2230
524 | 2231
525 | 2232
526 | 2233
527 | 2234
528 | 2235
529 | 2236
530 | 2237
531 | 2238
532 | 2239
533 | 2240
534 | 2241
535 | 2242
536 | 2243
537 | 2244
538 | 2245
539 | 2246
540 | 2247
541 | 2248
542 | 2249
543 | 2250
544 | 2251
545 | 2252
546 | 2253
547 | 2254
548 | 2255
549 | 2256
550 | 2257
551 | 2258
552 | 2259
553 | 2260
554 | 2261
555 | 2262
556 | 2263
557 | 2264
558 | 2265
559 | 2266
560 | 2267
561 | 2268
562 | 2269
563 | 2270
564 | 2271
565 | 2272
566 | 2273
567 | 2274
568 | 2275
569 | 2276
570 | 2277
571 | 2278
572 | 2279
573 | 2280
574 | 2281
575 | 2282
576 | 2283
577 | 2284
578 | 2285
579 | 2286
580 | 2287
581 | 2288
582 | 2289
583 | 2290
584 | 2291
585 | 2292
586 | 2293
587 | 2294
588 | 2295
589 | 2296
590 | 2297
591 | 2298
592 | 2299
593 | 2300
594 | 2301
595 | 2302
596 | 2303
597 | 2304
598 | 2305
599 | 2306
600 | 2307
601 | 2308
602 | 2309
603 | 2310
604 | 2311
605 | 2312
606 | 2313
607 | 2314
608 | 2315
609 | 2316
610 | 2317
611 | 2318
612 | 2319
613 | 2320
614 | 2321
615 | 2322
616 | 2323
617 | 2324
618 | 2325
619 | 2326
620 | 2327
621 | 2328
622 | 2329
623 | 2330
624 | 2331
625 | 2332
626 | 2333
627 | 2334
628 | 2335
629 | 2336
630 | 2337
631 | 2338
632 | 2339
633 | 2340
634 | 2341
635 | 2342
636 | 2343
637 | 2344
638 | 2345
639 | 2346
640 | 2347
641 | 2348
642 | 2349
643 | 2350
644 | 2351
645 | 2352
646 | 2353
647 | 2354
648 | 2355
649 | 2356
650 | 2357
651 | 2358
652 | 2359
653 | 2360
654 | 2361
655 | 2362
656 | 2363
657 | 2364
658 | 2365
659 | 2366
660 | 2367
661 | 2368
662 | 2369
663 | 2370
664 | 2371
665 | 2372
666 | 2373
667 | 2374
668 | 2375
669 | 2376
670 | 2377
671 | 2378
672 | 2379
673 | 2380
674 | 2381
675 | 2382
676 | 2383
677 | 2384
678 | 2385
679 | 2386
680 | 2387
681 | 2388
682 | 2389
683 | 2390
684 | 2391
685 | 2392
686 | 2393
687 | 2394
688 | 2395
689 | 2396
690 | 2397
691 | 2398
692 | 2399
693 | 2400
694 | 2401
695 | 2402
696 | 2403
697 | 2404
698 | 2405
699 | 2406
700 | 2407
701 | 2408
702 | 2409
703 | 2410
704 | 2411
705 | 2412
706 | 2413
707 | 2414
708 | 2415
709 | 2416
710 | 2417
711 | 2418
712 | 2419
713 | 2420
714 | 2421
715 | 2422
716 | 2423
717 | 2424
718 | 2425
719 | 2426
720 | 2427
721 | 2428
722 | 2429
723 | 2430
724 | 2431
725 | 2432
726 | 2433
727 | 2434
728 | 2435
729 | 2436
730 | 2437
731 | 2438
732 | 2439
733 | 2440
734 | 2441
735 | 2442
736 | 2443
737 | 2444
738 | 2445
739 | 2446
740 | 2447
741 | 2448
742 | 2449
743 | 2450
744 | 2451
745 | 2452
746 | 2453
747 | 2454
748 | 2455
749 | 2456
750 | 2457
751 | 2458
752 | 2459
753 | 2460
754 | 2461
755 | 2462
756 | 2463
757 | 2464
758 | 2465
759 | 2466
760 | 2467
761 | 2468
762 | 2469
763 | 2470
764 | 2471
765 | 2472
766 | 2473
767 | 2474
768 | 2475
769 | 2476
770 | 2477
771 | 2478
772 | 2479
773 | 2480
774 | 2481
775 | 2482
776 | 2483
777 | 2484
778 | 2485
779 | 2486
780 | 2487
781 | 2488
782 | 2489
783 | 2490
784 | 2491
785 | 2492
786 | 2493
787 | 2494
788 | 2495
789 | 2496
790 | 2497
791 | 2498
792 | 2499
793 | 2500
794 | 2501
795 | 2502
796 | 2503
797 | 2504
798 | 2505
799 | 2506
800 | 2507
801 | 2508
802 | 2509
803 | 2510
804 | 2511
805 | 2512
806 | 2513
807 | 2514
808 | 2515
809 | 2516
810 | 2517
811 | 2518
812 | 2519
813 | 2520
814 | 2521
815 | 2522
816 | 2523
817 | 2524
818 | 2525
819 | 2526
820 | 2527
821 | 2528
822 | 2529
823 | 2530
824 | 2531
825 | 2532
826 | 2533
827 | 2534
828 | 2535
829 | 2536
830 | 2537
831 | 2538
832 | 2539
833 | 2540
834 | 2541
835 | 2542
836 | 2543
837 | 2544
838 | 2545
839 | 2546
840 | 2547
841 | 2548
842 | 2549
843 | 2550
844 | 2551
845 | 2552
846 | 2553
847 | 2554
848 | 2555
849 | 2556
850 | 2557
851 | 2558
852 | 2559
853 | 2560
854 | 2561
855 | 2562
856 | 2563
857 | 2564
858 | 2565
859 | 2566
860 | 2567
861 | 2568
862 | 2569
863 | 2570
864 | 2571
865 | 2572
866 | 2573
867 | 2574
868 | 2575
869 | 2576
870 | 2577
871 | 2578
872 | 2579
873 | 2580
874 | 2581
875 | 2582
876 | 2583
877 | 2584
878 | 2585
879 | 2586
880 | 2587
881 | 2588
882 | 2589
883 | 2590
884 | 2591
885 | 2592
886 | 2593
887 | 2594
888 | 2595
889 | 2596
890 | 2597
891 | 2598
892 | 2599
893 | 2600
894 | 2601
895 | 2602
896 | 2603
897 | 2604
898 | 2605
899 | 2606
900 | 2607
901 | 2608
902 | 2609
903 | 2610
904 | 2611
905 | 2612
906 | 2613
907 | 2614
908 | 2615
909 | 2616
910 | 2617
911 | 2618
912 | 2619
913 | 2620
914 | 2621
915 | 2622
916 | 2623
917 | 2624
918 | 2625
919 | 2626
920 | 2627
921 | 2628
922 | 2629
923 | 2630
924 | 2631
925 | 2632
926 | 2633
927 | 2634
928 | 2635
929 | 2636
930 | 2637
931 | 2638
932 | 2639
933 | 2640
934 | 2641
935 | 2642
936 | 2643
937 | 2644
938 | 2645
939 | 2646
940 | 2647
941 | 2648
942 | 2649
943 | 2650
944 | 2651
945 | 2652
946 | 2653
947 | 2654
948 | 2655
949 | 2656
950 | 2657
951 | 2658
952 | 2659
953 | 2660
954 | 2661
955 | 2662
956 | 2663
957 | 2664
958 | 2665
959 | 2666
960 | 2667
961 | 2668
962 | 2669
963 | 2670
964 | 2671
965 | 2672
966 | 2673
967 | 2674
968 | 2675
969 | 2676
970 | 2677
971 | 2678
972 | 2679
973 | 2680
974 | 2681
975 | 2682
976 | 2683
977 | 2684
978 | 2685
979 | 2686
980 | 2687
981 | 2688
982 | 2689
983 | 2690
984 | 2691
985 | 2692
986 | 2693
987 | 2694
988 | 2695
989 | 2696
990 | 2697
991 | 2698
992 | 2699
993 | 2700
994 | 2701
995 | 2702
996 | 2703
997 | 2704
998 | 2705
999 | 2706
1000 | 2707
1001 |
--------------------------------------------------------------------------------
/unsupervised/data/cora/train.true:
--------------------------------------------------------------------------------
1 | 0
2 | 1
3 | 2
4 | 3
5 | 4
6 | 5
7 | 6
8 | 7
9 | 8
10 | 9
11 | 10
12 | 11
13 | 12
14 | 13
15 | 14
16 | 15
17 | 16
18 | 17
19 | 18
20 | 19
21 | 20
22 | 21
23 | 22
24 | 23
25 | 24
26 | 25
27 | 26
28 | 27
29 | 28
30 | 29
31 | 30
32 | 31
33 | 32
34 | 33
35 | 34
36 | 35
37 | 36
38 | 37
39 | 38
40 | 39
41 | 40
42 | 41
43 | 42
44 | 43
45 | 44
46 | 45
47 | 46
48 | 47
49 | 48
50 | 49
51 | 50
52 | 51
53 | 52
54 | 53
55 | 54
56 | 55
57 | 56
58 | 57
59 | 58
60 | 59
61 | 60
62 | 61
63 | 62
64 | 63
65 | 64
66 | 65
67 | 66
68 | 67
69 | 68
70 | 69
71 | 70
72 | 71
73 | 72
74 | 73
75 | 74
76 | 75
77 | 76
78 | 77
79 | 78
80 | 79
81 | 80
82 | 81
83 | 82
84 | 83
85 | 84
86 | 85
87 | 86
88 | 87
89 | 88
90 | 89
91 | 90
92 | 91
93 | 92
94 | 93
95 | 94
96 | 95
97 | 96
98 | 97
99 | 98
100 | 99
101 | 100
102 | 101
103 | 102
104 | 103
105 | 104
106 | 105
107 | 106
108 | 107
109 | 108
110 | 109
111 | 110
112 | 111
113 | 112
114 | 113
115 | 114
116 | 115
117 | 116
118 | 117
119 | 118
120 | 119
121 | 120
122 | 121
123 | 122
124 | 123
125 | 124
126 | 125
127 | 126
128 | 127
129 | 128
130 | 129
131 | 130
132 | 131
133 | 132
134 | 133
135 | 134
136 | 135
137 | 136
138 | 137
139 | 138
140 | 139
141 |
--------------------------------------------------------------------------------