├── NE.png └── README.md /NE.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/chihming/awesome-network-embedding/f6aa25a51d9d892cc79018881f89a06b02a522ba/NE.png -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # awesome-network-embedding 2 | [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome) 3 | [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) 4 | [![Gitter chat for developers at https://gitter.im/dmlc/xgboost](https://badges.gitter.im/Join%20Chat.svg)](https://gitter.im/awesome-network-embedding/Lobby) 5 | 6 | Also called network representation learning, graph embedding, knowledge embedding, etc. 7 | 8 | The task is to learn the representations of the vertices from a given network. 9 | 10 | CALL FOR HELP: I'm planning to re-organize the papers with clear classification index in the near future. Please feel free to submit a commit if you find any interesting related work:) 11 | 12 | 13 | 14 | # Paper References with the implementation(s) 15 | - **GraphGym** 16 | - A platform for designing and evaluating Graph Neural Networks (GNN), NeurIPS 2020 17 | - [[Paper]](https://proceedings.neurips.cc/paper/2020/file/c5c3d4fe6b2cc463c7d7ecba17cc9de7-Paper.pdf) 18 | - [[Python]](https://github.com/snap-stanford/graphgym) 19 | - **FEATHER** 20 | - Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models, CIKM 2020 21 | - [[Paper]](https://arxiv.org/abs/2005.07959) 22 | - [[Python]](https://github.com/benedekrozemberczki/FEATHER) 23 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 24 | - **HeGAN** 25 | - Adversarial Learning on Heterogeneous Information Networks, KDD 2019 26 | - [[Paper]](https://fangyuan1st.github.io/paper/KDD19_HeGAN.pdf) 27 | - [[Python]](https://github.com/librahu/HeGAN) 28 | - **NetMF** 29 | - Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and Node2Vec, WSDM 2018 30 | - [[Paper]](https://keg.cs.tsinghua.edu.cn/jietang/publications/WSDM18-Qiu-et-al-NetMF-network-embedding.pdf) 31 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 32 | - **GL2Vec** 33 | - GL2vec: Graph Embedding Enriched by Line Graphs with Edge Features, ICONIP 2019 34 | - [[Paper]](https://link.springer.com/chapter/10.1007/978-3-030-36718-3_1) 35 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 36 | - **NNSED** 37 | - A Non-negative Symmetric Encoder-Decoder Approach for Community Detection, CIKM 2017 38 | - [[Paper]](http://www.bigdatalab.ac.cn/~shenhuawei/publications/2017/cikm-sun.pdf) 39 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 40 | - **SymmNMF** 41 | - Symmetric Nonnegative Matrix Factorization for Graph Clustering, SDM 2012 42 | - [[Paper]](https://www.cc.gatech.edu/~hpark/papers/DaDingParkSDM12.pdf) 43 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 44 | - **RECT** 45 | - Network Embedding with Completely-Imbalanced Labels, TKDE 2020 46 | - [[Paper]](https://zhengwang100.github.io/pdf/TKDE20_wzheng.pdf) 47 | - [[Python]](https://github.com/zhengwang100/RECT) 48 | - **GEMSEC** 49 | - GEMSEC: Graph Embedding with Self Clustering, ASONAM 2019 50 | - [[Paper]](https://arxiv.org/abs/1802.03997) 51 | - [[Python]](https://github.com/benedekrozemberczki/GEMSEC) 52 | - **AmpliGraph** 53 | - Library for learning knowledge graph embeddings with TensorFlow 54 | - [[Project]](http://docs.ampligraph.org) 55 | - [[code]](https://github.com/Accenture/AmpliGraph) 56 | - **jodie** 57 | - Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks, KDD'19 58 | - [[Project]](http://snap.stanford.edu/jodie/) 59 | - [[Code]](https://github.com/srijankr/jodie/) 60 | - **PyTorch-BigGraph** 61 | - Pytorch-BigGraph - a distributed system for learning graph embeddings for large graphs, SysML'19 62 | - [[github]](https://github.com/facebookresearch/PyTorch-BigGraph) 63 | - **ATP** 64 | - ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation, AAAI'19 65 | - [[paper]](https://arxiv.org/abs/1811.00839) 66 | - [[code]](https://github.com/zhenv5/atp) 67 | - **MUSAE** 68 | - Multi-scale Attributed Node Embedding, ArXiv 2019 69 | - [[paper]](https://arxiv.org/abs/1909.13021) 70 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 71 | - [[Python]](https://github.com/benedekrozemberczki/MUSAE) 72 | - **SEAL-CI** 73 | - Semi-Supervised Graph Classification: A Hierarchical Graph Perspective, WWW'19 74 | - [[paper]](https://arxiv.org/pdf/1904.05003.pdf) 75 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/SEAL-CI) 76 | - **N-GCN and MixHop** 77 | - A Higher-Order Graph Convolutional Layer, NIPS'18 (workshop) 78 | - [[paper]](http://sami.haija.org/papers/high-order-gc-layer.pdf) 79 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/MixHop-and-N-GCN) 80 | - **CapsGNN** 81 | - Capsule Graph Neural Network, ICLR'19 82 | - [[paper]](https://openreview.net/forum?id=Byl8BnRcYm) 83 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/CapsGNN) 84 | - **Splitter** 85 | - Splitter: Learning Node Representations that Capture Multiple Social Contexts, WWW'19 86 | - [[paper]](http://epasto.org/papers/www2019splitter.pdf) 87 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/Splitter) 88 | - **REGAL** 89 | - REGAL: Representation Learning-based Graph Alignment. International Conference on Information and Knowledge Management, CIKM'18 90 | - [[arxiv]](https://arxiv.org/pdf/1802.06257.pdf) 91 | - [[paper]](https://dl.acm.org/citation.cfm?id=3271788) 92 | - [[code]](https://github.com/GemsLab/REGAL) 93 | - **PyTorch Geometric** 94 | - Fast Graph Representation Learning With PyTorch Geometric 95 | - [[paper]](https://arxiv.org/pdf/1903.02428.pdf) 96 | - [[Python PyTorch]](https://github.com/rusty1s/pytorch_geometric) 97 | - **TuckER** 98 | - Tensor Factorization for Knowledge Graph Completion, Arxiv'19 99 | - [[paper]](https://arxiv.org/pdf/1901.09590.pdf) 100 | - [[Python PyTorch]](https://github.com/ibalazevic/TuckER) 101 | - **HypER** 102 | - Hypernetwork Knowledge Graph Embeddings, Arxiv'18 103 | - [[paper]](https://arxiv.org/pdf/1808.07018.pdf) 104 | - [[Python PyTorch]](https://github.com/ibalazevic/HypER) 105 | - **GWNN** 106 | - Graph Wavelet Neural Network, ICLR'19 107 | - [[paper]](https://openreview.net/forum?id=H1ewdiR5tQ) 108 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork) 109 | - [[Python TensorFlow]](https://github.com/Eilene/GWNN) 110 | - **APPNP** 111 | - Combining Neural Networks with Personalized PageRank for Classification on Graphs, ICLR'19 112 | - [[paper]](https://arxiv.org/abs/1810.05997) 113 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/APPNP) 114 | - [[Python TensorFlow]](https://github.com/klicperajo/ppnp) 115 | - **role2vec** 116 | - Learning Role-based Graph Embeddings, IJCAI'18 117 | - [[paper]](https://arxiv.org/pdf/1802.02896.pdf) 118 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 119 | - [[Python]](https://github.com/benedekrozemberczki/role2vec) 120 | - **AttentionWalk** 121 | - Watch Your Step: Learning Node Embeddings via Graph Attention, NIPS'18 122 | - [[paper]](https://arxiv.org/pdf/1710.09599.pdf) 123 | - [[Python]](http://sami.haija.org/graph/context) 124 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/AttentionWalk) 125 | - [[Python TensorFlow]](https://github.com/google-research/google-research/tree/master/graph_embedding/watch_your_step/) 126 | - **GAT** 127 | - Graph Attention Networks, ICLR'18 128 | - [[paper]](https://arxiv.org/pdf/1710.10903.pdf) 129 | - [[Python PyTorch]](https://github.com/Diego999/pyGAT) 130 | - [[Python TensorFlow]](https://github.com/PetarV-/GAT) 131 | - **SINE** 132 | - SINE: Scalable Incomplete Network Embedding, ICDM'18 133 | - [[paper]](https://github.com/benedekrozemberczki/SINE/blob/master/paper.pdf) 134 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 135 | - [[Python PyTorch]](https://github.com/benedekrozemberczki/SINE/) 136 | - [[C++]](https://github.com/daokunzhang/SINE) 137 | - **SGCN** 138 | - Signed Graph Convolutional Network, ICDM'18 139 | - [[paper]](https://github.com/benedekrozemberczki/SGCN/blob/master/sgcn.pdf) 140 | - [[Python]](https://github.com/benedekrozemberczki/SGCN) 141 | - **TENE** 142 | - Enhanced Network Embedding with Text Information, ICPR'18 143 | - [[paper]](https://github.com/benedekrozemberczki/TENE/blob/master/tene_paper.pdf) 144 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 145 | - [[Python]](https://github.com/benedekrozemberczki/TENE) 146 | - **DANMF** 147 | - Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection, CIKM'18 148 | - [[paper]](https://smartyfh.com/Documents/18DANMF.pdf) 149 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 150 | - [[Python]](https://github.com/benedekrozemberczki/DANMF) 151 | - [[Matlab]](https://github.com/smartyfh/DANMF) 152 | - **BANE** 153 | - Binarized Attributed Network Embedding, ICDM'18 154 | - [[paper]](https://www.researchgate.net/publication/328688614_Binarized_Attributed_Network_Embedding) 155 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 156 | - [[Python]](https://github.com/benedekrozemberczki/BANE) 157 | - [[Matlab]](https://github.com/ICDM2018-BANE/BANE) 158 | - **GCN Insights** 159 | - Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning, AAAI'18 160 | - [[Project]](https://liqimai.github.io/blog/AAAI-18/) 161 | - [[code]](https://github.com/liqimai/gcn/tree/AAAI-18/) 162 | - **PCTADW** 163 | - Learning Embeddings of Directed Networks with Text-Associated Nodes---with Applications in Software Package Dependency Networks 164 | - [[paper]](https://arxiv.org/pdf/1809.02270.pdf) 165 | - [[Python]](https://github.com/shudan/PCTADW) 166 | - [[dataset]](https://doi.org/10.5281/zenodo.1410669) 167 | - **LGCN** 168 | - Large-Scale Learnable Graph Convolutional Networks, KDD'18 169 | - [[paper]](http://www.kdd.org/kdd2018/accepted-papers/view/large-scale-learnable-graph-convolutional-networks) 170 | - [[Python]](https://github.com/HongyangGao/LGCN) 171 | - **AspEm** 172 | - AspEm: Embedding Learning by Aspects in Heterogeneous Information Networks 173 | - [[paper]](http://yushi2.web.engr.illinois.edu/sdm18.pdf) 174 | - [[Python]](https://github.com/ysyushi/aspem) 175 | - **Walklets** 176 | - Don't Walk, Skip! Online Learning of Multi-scale Network Embeddings 177 | - [[paper]](https://arxiv.org/pdf/1605.02115.pdf) 178 | - [[Python Karateclub]](https://github.com/benedekrozemberczki/karateclub) 179 | - [[Python]](https://github.com/benedekrozemberczki/walklets) 180 | - **gat2vec** 181 | - gat2vec: Representation learning for attributed graphs 182 | - [[paper]](https://doi.org/10.1007/s00607-018-0622-9) 183 | - [[Python]](https://github.com/snash4/GAT2VEC) 184 | - **FSCNMF** 185 | - FSCNMF: Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks 186 | - [[paper]](https://arxiv.org/abs/1804.05313) 187 | - [[Python Karateclub]](https://github.com/benedekrozemberczki/karateclub) 188 | - [[Python]](https://github.com/sambaranban/FSCNMF) 189 | - [[Python]](https://github.com/benedekrozemberczki/FSCNMF) 190 | - **SIDE** 191 | - SIDE: Representation Learning in Signed Directed Networks 192 | - [[paper]](https://datalab.snu.ac.kr/side/resources/side.pdf) 193 | - [[Python]](https://datalab.snu.ac.kr/side/resources/side.zip) 194 | - [[Site]](https://datalab.snu.ac.kr/side/) 195 | - **AWE** 196 | - Anonymous Walk Embeddings, ICML'18 197 | - [[paper]](https://www.researchgate.net/publication/325114285_Anonymous_Walk_Embeddings) 198 | - [[Python]](https://github.com/nd7141/Anonymous-Walk-Embeddings) 199 | - **BiNE** 200 | - BiNE: Bipartite Network Embedding, SIGIR'18 201 | - [[paper]](http://staff.ustc.edu.cn/~hexn/papers/sigir18-bipartiteNE.pdf) 202 | - [[Python]](https://github.com/clhchtcjj/BiNE) 203 | - **HOPE** 204 | - Asymmetric Transitivity Preserving Graph Embedding 205 | - [[KDD 2016]](http://www.kdd.org/kdd2016/papers/files/rfp0184-ouA.pdf) 206 | - [[Python]](https://github.com/AnryYang/HOPE) 207 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 208 | - **VERSE** 209 | - VERSE, Versatile Graph Embeddings from Similarity Measures 210 | - [[Arxiv]](https://arxiv.org/abs/1803.04742) [[WWW 2018]] 211 | - [[Python]](https://github.com/xgfs/verse) 212 | - **AGNN** 213 | - Attention-based Graph Neural Network for semi-supervised learning 214 | - [[ICLR 2018 OpenReview (rejected)]](https://openreview.net/forum?id=rJg4YGWRb) 215 | - [[Python]](https://github.com/dawnranger/pytorch-AGNN) 216 | - **SEANO** 217 | - Semi-supervised Embedding in Attributed Networks with Outliers 218 | - [[Paper]](https://arxiv.org/pdf/1703.08100.pdf) (SDM 2018) 219 | - [[Python]](http://jiongqianliang.com/SEANO/) 220 | - **Hyperbolics** 221 | - Representation Tradeoffs for Hyperbolic Embeddings 222 | - [[Arxiv]](https://arxiv.org/abs/1804.03329) 223 | - [[Python]](https://github.com/HazyResearch/hyperbolics) 224 | - **DGCNN** 225 | - An End-to-End Deep Learning Architecture for Graph Classification 226 | - [[AAAI 2018]](http://www.cse.wustl.edu/~muhan/papers/AAAI_2018_DGCNN.pdf) 227 | - [[Lua]](https://github.com/muhanzhang/DGCNN) [[Python]](https://github.com/muhanzhang/pytorch_DGCNN) 228 | - **structure2vec** 229 | - Discriminative Embeddings of Latent Variable Models for Structured Data 230 | - [[Arxiv]](https://arxiv.org/abs/1603.05629) 231 | - [[Python]](https://github.com/Hanjun-Dai/pytorch_structure2vec) 232 | - **Decagon** 233 | - Decagon, Graph Neural Network for Multirelational Link Prediction 234 | - [[Arxiv]](https://arxiv.org/abs/1802.00543) [[SNAP]](http://snap.stanford.edu/decagon/) [[ISMB 2018]] 235 | - [[Python]](https://github.com/marinkaz/decagon) 236 | - **DHNE** 237 | - Structural Deep Embedding for Hyper-Networks 238 | - [[AAAI 2018]](http://nrl.thumedialab.com/Structural-Deep-Embedding-for-Hyper-Networks)[[Arxiv]](https://arxiv.org/abs/1711.10146) 239 | - [[Python]](https://github.com/tadpole/DHNE) 240 | - **Ohmnet** 241 | - Feature Learning in Multi-Layer Networks 242 | - [[Arxiv]](https://arxiv.org/abs/1707.04638) [[SNAP]](http://snap.stanford.edu/ohmnet/) 243 | - [[Python]](https://github.com/marinkaz/ohmnet) 244 | - **SDNE** 245 | - Structural Deep Network Embedding 246 | - [[KDD 2016]](http://www.kdd.org/kdd2016/papers/files/rfp0191-wangAemb.pdf) 247 | - [[Python]](https://github.com/xiaohan2012/sdne-keras) 248 | - **STWalk** 249 | - STWalk: Learning Trajectory Representations in Temporal Graphs] 250 | - [[Arxiv]](https://arxiv.org/abs/1711.04150) 251 | - [[Python]](https://github.com/supriya-pandhre/STWalk) 252 | - **LoNGAE** 253 | - Learning to Make Predictions on Graphs with Autoencoders 254 | - [[Arxiv]](https://arxiv.org/abs/1802.08352) 255 | - [[Python]](https://github.com/vuptran/graph-representation-learning) 256 | - **RSDNE** 257 | - [RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-imbalanced Labels for Network Embedding.](https://zhengwang100.github.io/AAAI18_RSDNE.pdf), AAAI 2018 258 | - [[Matlab]](https://github.com/zhengwang100/RSDNE) 259 | - **FastGCN** 260 | - FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling 261 | - [[Arxiv]](https://arxiv.org/abs/1801.10247), [[ICLR 2018 OpenReview]](https://openreview.net/forum?id=rytstxWAW) 262 | - [[Python]](https://github.com/matenure/FastGCN) 263 | - **diff2vec** 264 | - [Fast Sequence Based Embedding with Diffusion Graphs](http://homepages.inf.ed.ac.uk/s1668259/papers/sequence.pdf), CompleNet 2018 265 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 266 | - [[Python]](https://github.com/benedekrozemberczki/diff2vec) 267 | - **Poincare** 268 | - [Poincaré Embeddings for Learning Hierarchical Representations](https://papers.nips.cc/paper/7213-poincare-embeddings-for-learning-hierarchical-representations), NIPS 2017 269 | - [[PyTorch]](https://github.com/facebookresearch/poincare-embeddings) [[Python]](https://radimrehurek.com/gensim/models/poincare.html) [[C++]](https://github.com/TatsuyaShirakawa/poincare-embedding) 270 | - **PEUNE** 271 | - [PRUNE: Preserving Proximity and Global Ranking for Network Embedding](https://papers.nips.cc/paper/7110-prune-preserving-proximity-and-global-ranking-for-network-embedding), NIPS 2017 272 | - [[code]](https://github.com/ntumslab/PRUNE) 273 | - **ASNE** 274 | - Attributed Social Network Embedding, TKDE'18 275 | - [[arxiv]](https://arxiv.org/abs/1706.01860) 276 | - [[Python]](https://github.com/lizi-git/ASNE) 277 | - [[Fast Python]](https://github.com/benedekrozemberczki/ASNE) 278 | - **GraphWave** 279 | - [Spectral Graph Wavelets for Structural Role Similarity in Networks](http://snap.stanford.edu/graphwave/), 280 | - [[arxiv]](https://arxiv.org/abs/1710.10321), [[ICLR 2018 OpenReview]](https://openreview.net/forum?id=rytstxWAW) 281 | - [[Python]](https://github.com/snap-stanford/graphwave) [[faster version]](https://github.com/benedekrozemberczki/GraphWaveMachine) 282 | - **StarSpace** 283 | - [StarSpace: Embed All The Things!](https://arxiv.org/pdf/1709.03856), arxiv'17 284 | - [[code]](https://github.com/facebookresearch/Starspace) 285 | - **proNet-core** 286 | - Vertex-Context Sampling for Weighted Network Embedding, arxiv'17 287 | - [[arxiv]](https://arxiv.org/abs/1711.00227) [[code]](https://github.com/cnclabs/proNet-core) 288 | - **struc2vec** 289 | - [struc2vec: Learning Node Representations from Structural Identity](https://dl.acm.org/citation.cfm?id=3098061), KDD'17 290 | - [[Python]](https://github.com/leoribeiro/struc2vec) 291 | - **ComE** 292 | - Learning Community Embedding with Community Detection and Node Embedding on Graphs, CIKM'17 293 | - [[Python]](https://github.com/andompesta/ComE) 294 | - **BoostedNE** 295 | - [Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximation](https://arxiv.org/abs/1808.08627), '18 296 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 297 | - [[Python]](https://github.com/benedekrozemberczki/BoostedFactorization) 298 | - **M-NMF** 299 | - Community Preserving Network Embedding, AAAI'17 300 | - [[Python TensorFlow]](https://github.com/benedekrozemberczki/M-NMF) 301 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 302 | - **GraphSAGE** 303 | - Inductive Representation Learning on Large Graphs, NIPS'17 304 | - [[arxiv]](https://arxiv.org/abs/1706.02216) [[TF]](https://github.com/williamleif/GraphSAGE) [[PyTorch]](https://github.com/williamleif/graphsage-simple/) 305 | - **ICE** 306 | - [ICE: Item Concept Embedding via Textual Information](http://dl.acm.org/citation.cfm?id=3080807), SIGIR'17 307 | - [[demo]](https://cnclabs.github.io/ICE/) [[code]](https://github.com/cnclabs/ICE) 308 | - **GuidedHeteEmbedding** 309 | - Task-guided and path-augmented heterogeneous network embedding for author identification, WSDM'17 310 | - [[paper]](https://arxiv.org/pdf/1612.02814.pdf) [[code]](https://github.com/chentingpc/GuidedHeteEmbedding) 311 | - **metapath2vec** 312 | - metapath2vec: Scalable Representation Learning for Heterogeneous Networks, KDD'17 313 | - [[paper]](https://www3.nd.edu/~dial/publications/dong2017metapath2vec.pdf) [[project website]](https://ericdongyx.github.io/metapath2vec/m2v.html) 314 | - **GCN** 315 | - Semi-Supervised Classification with Graph Convolutional Networks, ICLR'17 316 | - [[arxiv]](https://arxiv.org/abs/1609.02907) [[Python Tensorflow]](https://github.com/tkipf/gcn) 317 | - **GAE** 318 | - Variational Graph Auto-Encoders, arxiv 319 | - [[arxiv]](https://arxiv.org/abs/1611.07308) [[Python Tensorflow]](https://github.com/tkipf/gae) 320 | - **CANE** 321 | - CANE: Context-Aware Network Embedding for Relation Modeling, ACL'17 322 | - [[paper]](http://www.thunlp.org/~tcc/publications/acl2017_cane.pdf) [[Python]](https://github.com/thunlp/cane) 323 | - **TransNet** 324 | - TransNet: Translation-Based Network Representation Learning for Social Relation Extraction, IJCAI'17 325 | - [[Python Tensorflow]](https://github.com/thunlp/TransNet) 326 | - **cnn_graph** 327 | - Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering, NIPS'16 328 | - [[Python]](https://github.com/mdeff/cnn_graph) 329 | - **ConvE** 330 | - [Convolutional 2D Knowledge Graph Embeddings](https://arxiv.org/pdf/1707.01476v2.pdf), arxiv 331 | - [[source]](https://github.com/TimDettmers/ConvE) 332 | - **node2vec** 333 | - [node2vec: Scalable Feature Learning for Networks](http://dl.acm.org/citation.cfm?id=2939672.2939754), KDD'16 334 | - [[arxiv]](https://arxiv.org/abs/1607.00653) [[Python]](https://github.com/aditya-grover/node2vec) [[Python-2]](https://github.com/apple2373/node2vec) [[Python-3]](https://github.com/eliorc/node2vec) [[C++]](https://github.com/xgfs/node2vec-c) 335 | - **DNGR** 336 | - [Deep Neural Networks for Learning Graph Representations](http://www.aaai.org/ocs/index.php/AAAI/AAAI16/paper/view/12423), AAAI'16 337 | - [[Matlab]](https://github.com/ShelsonCao/DNGR) [[Python Keras]](https://github.com/MdAsifKhan/DNGR-Keras) 338 | - **HolE** 339 | - [Holographic Embeddings of Knowledge Graphs](http://dl.acm.org/citation.cfm?id=3016172), AAAI'16 340 | - [[Python-sklearn]](https://github.com/mnick/holographic-embeddings) [[Python-sklearn2]](https://github.com/mnick/scikit-kge) 341 | - **ComplEx** 342 | - [Complex Embeddings for Simple Link Prediction](http://dl.acm.org/citation.cfm?id=3045609), ICML'16 343 | - [[arxiv]](https://arxiv.org/abs/1606.06357) [[Python]](https://github.com/ttrouill/complex) 344 | - **MMDW** 345 | - Max-Margin DeepWalk: Discriminative Learning of Network Representation, IJCAI'16 346 | - [[paper]](http://nlp.csai.tsinghua.edu.cn/~lzy/publications/ijcai2016_mmdw.pdf) [[Java]](https://github.com/thunlp/MMDW) 347 | - **planetoid** 348 | - Revisiting Semi-supervised Learning with Graph Embeddings, ICML'16 349 | - [[arxiv]](https://arxiv.org/abs/1603.08861) [[Python]](https://github.com/kimiyoung/planetoid) 350 | - **graph2vec** 351 | - graph2vec: Learning Distributed Representations of Graphs, KDD'17 MLGWorkshop 352 | - [[arxiv]](https://arxiv.org/abs/1707.05005) 353 | - [[Python gensim]](https://github.com/benedekrozemberczki/graph2vec) [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 354 | - **PowerWalk** 355 | - [PowerWalk: Scalable Personalized PageRank via Random Walks with Vertex-Centric Decomposition](http://dl.acm.org/citation.cfm?id=2983713), CIKM'16 356 | - [[code]](https://github.com/lqhl/PowerWalk) 357 | - **LINE** 358 | - [LINE: Large-scale information network embedding](http://dl.acm.org/citation.cfm?id=2741093), WWW'15 359 | - [[arxiv]](https://arxiv.org/abs/1503.03578) [[C++]](https://github.com/tangjianpku/LINE) [[Python TF]](https://github.com/snowkylin/line) [[Python Theano/Keras]](https://github.com/VahidooX/LINE) 360 | - **PTE** 361 | - [PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks](http://dl.acm.org/citation.cfm?id=2783307), KDD'15 362 | - [[C++]](https://github.com/mnqu/PTE) 363 | - **GraRep** 364 | - [Grarep: Learning graph representations with global structural information](http://dl.acm.org/citation.cfm?id=2806512), CIKM'15 365 | - [[Matlab]](https://github.com/ShelsonCao/GraRep) 366 | - [[Julia]](https://github.com/xgfs/GraRep.jl) 367 | - [[Python]](https://github.com/benedekrozemberczki/GraRep) 368 | - [[Python KarateClub]](https://github.com/benedekrozemberczki/karateclub) 369 | - **KB2E** 370 | - [Learning Entity and Relation Embeddings for Knowledge Graph Completion](http://dl.acm.org/citation.cfm?id=2886624), AAAI'15 371 | - [[paper]](http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf) [[C++]](https://github.com/thunlp/KB2E) [[faster version]](https://github.com/thunlp/Fast-TransX) 372 | - **TADW** 373 | - [Network Representation Learning with Rich Text Information](http://dl.acm.org/citation.cfm?id=2832542), IJCAI'15 374 | - [[paper]](https://www.ijcai.org/Proceedings/15/Papers/299.pdf) [[Matlab]](https://github.com/thunlp/tadw) [[Python]](https://github.com/benedekrozemberczki/TADW) 375 | - **DeepWalk** 376 | - [DeepWalk: Online Learning of Social Representations](http://dl.acm.org/citation.cfm?id=2623732), KDD'14 377 | - [[arxiv]](https://arxiv.org/abs/1403.6652) [[Python]](https://github.com/phanein/deepwalk) [[C++]](https://github.com/xgfs/deepwalk-c) 378 | - **GEM** 379 | - Graph Embedding Techniques, Applications, and Performance: A Survey 380 | - [[arxiv]](https://arxiv.org/abs/1705.02801) [[Python]](https://github.com/palash1992/GEM) 381 | - **DNE-SBP** 382 | - Deep Network Embedding for Graph Representation Learning in Signed Networks 383 | - [[paper]](https://ieeexplore.ieee.org/document/8486671) [[Code]](https://github.com/shenxiaocam/Deep-network-embedding-for-graph-representation-learning-in-signed-networks) 384 | 385 | # Paper References 386 | 387 | [A Comprehensive Survey on Graph Neural Networks](https://arxiv.org/abs/1901.00596), arxiv'19 388 | 389 | [Hierarchical Graph Representation Learning with Differentiable Pooling](https://arxiv.org/pdf/1806.08804.pdf), NIPS'18 390 | 391 | **SEMAC**, [Link Prediction via Subgraph Embedding-Based Convex Matrix Completion](https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16442), AAAI 2018, [Slides](https://www.slideshare.net/gdm3003/semac-graph-node-embeddings-for-link-prediction) 392 | 393 | **MILE**, [MILE: A Multi-Level Framework for Scalable Graph Embedding](https://arxiv.org/pdf/1802.09612.pdf), arxiv'18 394 | 395 | **MetaGraph2Vec**, [MetaGraph2Vec: Complex Semantic Path Augmented Heterogeneous Network Embedding](https://arxiv.org/abs/1803.02533) 396 | 397 | **PinSAGE**, [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://arxiv.org/abs/1806.01973) 398 | 399 | [Curriculum Learning for Heterogeneous Star Network Embedding via Deep Reinforcement Learning](https://dl.acm.org/citation.cfm?id=3159711), WSDM '18 400 | 401 | [Adversarial Network Embedding](https://arxiv.org/abs/1711.07838), arxiv 402 | 403 | **Role2Vec**, [Learning Role-based Graph Embeddings](https://arxiv.org/abs/1802.02896) 404 | 405 | **edge2vec**, [Feature Propagation on Graph: A New Perspective to Graph Representation 406 | Learning](https://arxiv.org/abs/1804.06111) 407 | 408 | **MINES**, [Multi-Dimensional Network Embedding with Hierarchical Structure](http://cse.msu.edu/~mayao4/downloads/Multidimensional_Network_Embedding_with_Hierarchical_Structure.pdf) 409 | 410 | [Walk-Steered Convolution for Graph Classification](https://arxiv.org/abs/1804.05837) 411 | 412 | [Deep Feature Learning for Graphs](https://arxiv.org/abs/1704.08829), arxiv'17 413 | 414 | [Fast Linear Model for Knowledge Graph Embeddings](https://arxiv.org/abs/1710.10881), arxiv'17 415 | 416 | [Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec](https://arxiv.org/abs/1710.02971), arxiv'17 417 | 418 | [A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications](https://arxiv.org/abs/1709.07604), arxiv'17 419 | 420 | [Representation Learning on Graphs: Methods and Applications](https://arxiv.org/pdf/1709.05584.pdf), IEEE DEB'17 421 | 422 | **CONE**, [CONE: Community Oriented Network Embedding](https://arxiv.org/abs/1709.01554), arxiv'17 423 | 424 | **LANE**, 425 | [Label Informed Attributed Network Embedding](http://dl.acm.org/citation.cfm?id=3018667), WSDM'17 426 | 427 | **Graph2Gauss**, 428 | [Deep Gaussian Embedding of Attributed Graphs: Unsupervised Inductive Learning via Ranking](https://arxiv.org/abs/1707.03815), arxiv 429 | [[Bonus Animation]](https://twitter.com/abojchevski/status/885502050133585925) 430 | 431 | [Scalable Graph Embedding for Asymmetric Proximity](https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14696), AAAI'17 432 | 433 | [Query-based Music Recommendations via Preference Embedding](http://dl.acm.org/citation.cfm?id=2959169), RecSys'16 434 | 435 | [Tri-party deep network representation](http://dl.acm.org/citation.cfm?id=3060886), IJCAI'16 436 | 437 | [Heterogeneous Network Embedding via Deep Architectures](http://dl.acm.org/citation.cfm?id=2783296), KDD'15 438 | 439 | [Neural Word Embedding As Implicit Matrix Factorization](http://dl.acm.org/citation.cfm?id=2969070), NIPS'14 440 | 441 | [Distributed large-scale natural graph factorization](http://dl.acm.org/citation.cfm?id=2488393), WWW'13 442 | 443 | [From Node Embedding To Community Embedding](https://arxiv.org/abs/1610.09950), arxiv 444 | 445 | [Walklets: Multiscale Graph Embeddings for Interpretable Network Classification](https://arxiv.org/abs/1605.02115), arxiv 446 | 447 | [Comprehend DeepWalk as Matrix Factorization](https://arxiv.org/abs/1501.00358), arxiv 448 | 449 | # Conference & Workshop 450 | 451 | [Graph Neural Networks for Natural Language Processing](https://github.com/svjan5/GNNs-for-NLP), **EMNLP'19** 452 | 453 | [SMORe : Modularize Graph Embedding for Recommendation](https://github.com/cnclabs/smore), **RecSys'19** 454 | 455 | [13th International Workshop on Mining and Learning with Graphs](http://www.mlgworkshop.org/2017/), **MLG'17** 456 | 457 | [WWW-18 Tutorial Representation Learning on Networks](http://snap.stanford.edu/proj/embeddings-www/), **WWW'18** 458 | 459 | # Related List 460 | 461 | [awesome-graph-classification](https://github.com/benedekrozemberczki/awesome-graph-classification) 462 | 463 | [awesome-community-detection](https://github.com/benedekrozemberczki/awesome-community-detection) 464 | 465 | [awesome-embedding-models](https://github.com/Hironsan/awesome-embedding-models) 466 | 467 | [Must-read papers on network representation learning (NRL) / network embedding (NE)](https://github.com/thunlp/NRLPapers) 468 | 469 | [Must-read papers on knowledge representation learning (KRL) / knowledge embedding (KE)](https://github.com/thunlp/KRLPapers) 470 | 471 | [Network Embedding Resources](https://github.com/nate-russell/Network-Embedding-Resources) 472 | 473 | [awesome-embedding-models](https://github.com/Hironsan/awesome-embedding-models) 474 | 475 | [2vec-type embedding models](https://github.com/MaxwellRebo/awesome-2vec) 476 | 477 | [Must-read papers on GNN](https://github.com/thunlp/GNNPapers) 478 | 479 | [LiteratureDL4Graph](https://github.com/DeepGraphLearning/LiteratureDL4Graph) 480 | 481 | [awesome-graph-classification](https://github.com/benedekrozemberczki/awesome-graph-classification) 482 | 483 | # Related Project 484 | 485 | **Stanford Network Analysis Project** [website](http://snap.stanford.edu/) 486 | 487 | **StellarGraph Machine Learning Library** [website](https://www.stellargraph.io) [GitHub](https://github.com/stellargraph/stellargraph) 488 | --------------------------------------------------------------------------------