└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Graph Learning Notes (In Chinese) 2 | 3 | 在此整理了一些个人的文献阅读笔记，主要是图学习领域的，希望大家多多指正。 4 | 5 | 6 | ## Survey 7 | 8 | * Graph self-supervised learning: A survey (**TKDE 2022**) [[paper](https://arxiv.org/pdf/2103.00111.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120686123?spm=1001.2014.3001.5502)] 9 | 10 | * 面向社会计算的网络表示学习 (**清华博士论文 2018**) [[paper](http://nlp.csai.tsinghua.edu.cn/~tcc/publications/phd_thesis.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/121908132?spm=1001.2014.3001.5501)] 11 | 12 | * A Survey on Network Embedding (**AAAI 2017**) [[paper](http://shichuan.org/hin/topic/Embedding/2017.%20A%20Survey%20on%20Network%20Embedding.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/104563890)] 13 | 14 | * 网络表示学习专题 (**CCF 2017**) [[note](https://blog.csdn.net/CSDNTianJi/article/details/103815322)] 15 | 16 | ## Paper 17 | 18 | ### 2023 19 | 20 | * Heterogeneous Graph Learning for Acoustic Event Classification (**ICASSP**) [[paper](https://arxiv.org/pdf/2303.02665)][[code](https://github.com/AmirSh15/Cross_modality_graph)][[note](https://blog.csdn.net/CSDNTianJi/article/details/132825026?spm=1001.2014.3001.5501)] 21 | 22 | ### 2022 23 | 24 | * Neighborhood-aware Scalable Temporal Network Representation Learning (**LOG**) [[paper](https://proceedings.mlr.press/v198/luo22a/luo22a.pdf)][[code](https://github.com/Graph-COM/Neighborhood-Aware-Temporal-Network)][note](https://blog.csdn.net/CSDNTianJi/article/details/133634640?spm=1001.2014.3001.5501)] 25 | 26 | * GraphMAE: Self-Supervised Masked Graph Autoencoders (**KDD**) [[paper](https://arxiv.org/pdf/2205.10803.pdf)][[code](https://github.com/THUDM/GraphMAE)][note](https://blog.csdn.net/CSDNTianJi/article/details/129635392?spm=1001.2014.3001.5501)] 27 | 28 | * ROLAND: Graph Learning Framework for Dynamic Graphs (**KDD**) [[paper](https://arxiv.org/abs/2208.07239)][[code](https://github.com/snap-stanford/roland)][[note](https://blog.csdn.net/CSDNTianJi/article/details/127508775)] 29 | 30 | * SAIL: Self Augmented Graph Contrastive Learning (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/20875)][[note](https://blog.csdn.net/CSDNTianJi/article/details/127030633?spm=1001.2014.3001.5501)] 31 | 32 | * TREND: TempoRal Event and Node Dynamics for Graph Representation Learning (**WWW**) [[paper](https://arxiv.org/pdf/2203.14303.pdf)][[code](https://github.com/WenZhihao666/TREND)][[note](https://blog.csdn.net/CSDNTianJi/article/details/126859612?spm=1001.2014.3001.5501)] 33 | 34 | * CGC: Contrastive Graph Clustering for Community Detection and Tracking (**WWW**) [[paper](https://dl.acm.org/doi/abs/10.1145/3485447.3512160)][[note](https://blog.csdn.net/CSDNTianJi/article/details/126083177?spm=1001.2014.3001.5501)] 35 | 36 | * Pre-Training on Dynamic Graph Neural Networks (**Neurocomputing**) [[paper](https://arxiv.org/pdf/2102.12380.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120711689)] 37 | 38 | ### 2021 39 | 40 | * Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer (**CIKM**) [[paper](https://arxiv.org/pdf/2108.06625)][[code](https://github.com/DyGRec/TGSRec)][[note](https://blog.csdn.net/CSDNTianJi/article/details/132993073?spm=1001.2014.3001.5501)] 41 | 42 | * Do Transformers Really Perform Bad for Graph Representation (**NeurIPS**) [[paper](https://proceedings.neurips.cc/paper/2021/hash/f1c1592588411002af340cbaedd6fc33-Abstract.html)][[code](https://github.com/Microsoft/Graphormer)][[note](https://blog.csdn.net/CSDNTianJi/article/details/123595047?spm=1001.2014.3001.5501)] 43 | 44 | * Structural Deep Clustering Network (**WWW**) [[paper](https://arxiv.org/pdf/2002.01633.pdf)][[code](https://github.com/bdy9527/SDCN)][[note](https://blog.csdn.net/CSDNTianJi/article/details/123323126?spm=1001.2014.3001.5501)] 45 | 46 | * Deep Fusion Clustering Network (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/17198)][[code](https://github.com/WxTu/DFCN)][[note](https://blog.csdn.net/CSDNTianJi/article/details/123155242?spm=1001.2014.3001.5501)] 47 | 48 | * Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks (**ICLR**) [[paper](https://arxiv.org/pdf/2101.05974.pdf)][[code](https://github.com/snap-stanford/CAW)][[note](https://blog.csdn.net/CSDNTianJi/article/details/114488437)] 49 | 50 | * Overcoming Catastrophic Forgetting in Graph Neural Networks with Experience Replay (**AAAI**) [[paper](https://www.aaai.org/AAAI21Papers/AAAI-4967.ZhouF.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/114436739)] 51 | 52 | * Combining Label Propagation and Simple Models Out-performs Graph Neural Networks (**ICLR**) [[paper](https://arxiv.org/pdf/2010.13993.pdf)][[code](https://github.com/CUAI/CorrectAndSmooth)][[note](https://blog.csdn.net/CSDNTianJi/article/details/114632230)] 53 | 54 | * Accurate Learning of Graph Representations with Graph Multiset Pooling (**ICLR**) [[paper](https://arxiv.org/pdf/2102.11533.pdf)][[code](https://github.com/JinheonBaek/GMT)][[note](https://blog.csdn.net/CSDNTianJi/article/details/115186068)] 55 | 56 | * Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting (**AAAI Best Paper**) [[paper](https://www.aaai.org/AAAI21Papers/AAAI-7346.ZhouHaoyi.pdf)][[code](https://github.com/zhouhaoyi/Informer2020)][[note](https://blog.csdn.net/CSDNTianJi/article/details/116326599)] 57 | 58 | * Self-supervised Graph Learning for Recommendation (**SIGIR**) [[paper](https://arxiv.org/pdf/2010.10783.pdf)][[code](https://github.com/wujcan/SGL-TensorFlow)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120121426)] 59 | 60 | * Learnable Embedding Sizes for Recommender Systems (**ICLR**) [[paper](https://arxiv.org/pdf/2101.07577.pdf)][[code](https://github.com/ssui-liu/learnable-embed-sizes-for-RecSys)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120471847)] 61 | 62 | * Adversarial Directed Graph Embedding (**AAAI**) [[paper](https://www.aaai.org/AAAI21Papers/AAAI-2842.ZhuShijie.pdf)][[code](https://github.com/RingBDStack/DGGAN)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120517065)] 63 | 64 | * Graph Game Embedding (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/16942)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120815394)] 65 | 66 | * Towards Robust Graph Contrastive Learning (**WWW Workshop**) [[paper](https://arxiv.org/pdf/2102.13085.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120889575)] 67 | 68 | * Towards open-world feature extrapolation: An inductive graph learning approach (**NeurIPS**) [[paper](https://proceedings.neurips.cc/paper/2021/file/a1c5aff9679455a233086e26b72b9a06-Paper.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/122962734)] 69 | 70 | * Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis (**ACL**) [[paper](https://aclanthology.org/2021.acl-long.494/)][[code](https://github.com/CCChenhao997/DualGCN-ABSA)][[note](https://blog.csdn.net/CSDNTianJi/article/details/123523198)] 71 | 72 | * How to Find Your Friendly Neighborhood: Graph Attention Design with Self-supervision (**ICLR**) [[paper](https://arxiv.org/abs/2204.04879)][[code](https://github.com/dongkwan-kim/SuperGAT)][[note](https://blog.csdn.net/CSDNTianJi/article/details/114578725)] 73 | 74 | ### 2020 75 | 76 | * Contrastive Multi-View Representation Learning on Graphs (**ICML**) [[paper](http://proceedings.mlr.press/v119/hassani20a/hassani20a.pdf)][[code](https://github.com/kavehhassani/mvgrl)][[note](https://blog.csdn.net/CSDNTianJi/article/details/129653972?spm=1001.2014.3001.5501)] 77 | 78 | * Temporal Graph Networks for Deep Learning on Dynamic Graphs (**ICML Workshop**) [[paper](https://arxiv.org/abs/2006.10637)][[code](https://github.com/twitter-research/tgn)][[note](https://blog.csdn.net/CSDNTianJi/article/details/127846239?spm=1001.2014.3001.5501)] 79 | 80 | * Inductive representation learning on temporal graphs (**ICLR**) [[paper](https://arxiv.org/abs/2002.07962)][[code](https://github.com/StatsDLMathsRecomSys/Inductive-representation-learning-on-temporal-graphs)][[note](https://blog.csdn.net/CSDNTianJi/article/details/104325966)] 81 | 82 | * EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graph (**AAAI**) [[paper](https://ojs.aaai.org/index.php/AAAI/article/view/5984)][[code](https://github.com/IBM/EvolveGCN)][[note](https://blog.csdn.net/CSDNTianJi/article/details/108708828)] 83 | 84 | * DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks (**WSDM**) [[paper](http://yhwu.me/publications/dysat_wsdm20.pdf)][[code](https://github.com/aravindsankar28/DySAT)][[note](https://blog.csdn.net/CSDNTianJi/article/details/109530388)] 85 | 86 | * Inductive and Unsupervised Representation Learning on Graph Structured Objects (**ICLR**) [[paper](https://openreview.net/forum?id=rkem91rtDB)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110006234)] 87 | 88 | * Continuous-Time Dynamic Graph Learning via Neural Interaction Processes (**CIKM**) [[note](https://blog.csdn.net/CSDNTianJi/article/details/116721279)] 89 | 90 | * GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training (**KDD**) [[paper](https://arxiv.org/pdf/2006.09963.pdf)][[code](https://github.com/THUDM/GCC)][[note](https://blog.csdn.net/CSDNTianJi/article/details/108692278)] 91 | 92 | * JNET: Learning User Representations via Joint Network Embedding and Topic Embedding (**WSDM**) [[paper](https://dl.acm.org/doi/abs/10.1145/3336191.3371770)][[code](https://github.com/Linda-sunshine/JNET)][[note](https://blog.csdn.net/CSDNTianJi/article/details/113574487)] 93 | 94 | * Deep Graph Contrastive Representation Learning (**ICML Workshop**) [[paper](https://arxiv.org/pdf/2006.04131.pdf)][[code](https://github.com/CRIPAC-DIG/GRACE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/120843409)] 95 | 96 | * On the equivalence between positional node embeddings and structural graph representations (**ICLR**) [[paper](https://arxiv.org/pdf/1910.00452.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/105512163)] 97 | 98 | * Explain Graph Neural Networks to Understand Weight Graph Features (**IFIP**) [[paper](https://arxiv.org/pdf/2002.00514.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110005728)] 99 | 100 | ### 2019 101 | 102 | * DyREP: Learing Representations over Dynamic Graphs (**ICLR**) [[paper](https://openreview.net/forum?id=HyePrhR5KX)][[note](https://blog.csdn.net/CSDNTianJi/article/details/103844015)] 103 | 104 | * Self-attention with Functional Time Representation Learning (**NeurIPS**) [[paper](https://proceedings.neurips.cc/paper/2019/file/cf34645d98a7630e2bcca98b3e29c8f2-Paper.pdf)][[code](https://github.com/StatsDLMathsRecomSys/Self-attention-with-Functional-Time-Representation-Learning)][[note](https://blog.csdn.net/CSDNTianJi/article/details/105678080)] 105 | 106 | * Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks (**KDD**) [[paper](https://cs.stanford.edu/~srijan/pubs/jodie-kdd2019.pdf)][[code](https://github.com/srijankr/jodie)][[slide](https://cs.stanford.edu/~srijan/pubs/jodie-kdd2019-slides.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/105892100)] 107 | 108 | * Node Embedding over Temporal Graphs (**IJCAI**) [[paper](https://www.ijcai.org/proceedings/2019/0640.pdf)][[code](https://github.com/urielsinger/tNodeEmbed)][[note](https://blog.csdn.net/CSDNTianJi/article/details/107761204)] 109 | 110 | * Spatio-Temporal Attentive RNN for Node Classification in Temporal Attributed Graph (**IJCAI**) [[paper](https://www.ijcai.org/proceedings/2019/0548.pdf)][[code](https://github.com/DerronXu/STAR)][[note](https://blog.csdn.net/CSDNTianJi/article/details/108573691)] 111 | 112 | * GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding (**WWW**) [[paper](https://arxiv.org/pdf/1903.00757.pdf)][[code](https://github.com/DeepGraphLearning/graphvite)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110006408)] 113 | 114 | ### 2018 115 | 116 | * Continuous-Time Dynamic Network Embeddings (**WWW**) [[paper](https://dl.acm.org/doi/pdf/10.1145/3184558.3191526)][[code](https://github.com/Shubhranshu-Shekhar/ctdne)][[note](https://blog.csdn.net/CSDNTianJi/article/details/100830263)] 117 | 118 | * Embedding Temporal Network via Neighborhood Formation (**KDD**) [[paper](http://www.shichuan.org/hin/topic/Embedding/2018.KDD%202018%20Embedding%20Temporal%20Network%20via%20Neighborhood%20Formation.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/101921040)] 119 | 120 | * Learning dynamic embeddings from temporal interactions (**arXiv**) [[paper](https://arxiv.org/pdf/1812.02289.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/104859498)] 121 | 122 | * Arbitrary-Order Proximity Preserved Network Embedding (**KDD**) [[paper](https://pengcui.thumedialab.com/papers/NE-ArbitraryProximity.pdf)][[code](https://github.com/ZW-ZHANG/AROPE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/103857531)] 123 | 124 | * A Unified Framework for Community Detection and Network Representation Learning (**TKDE**) [[paper](https://arxiv.org/pdf/1611.06645.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110952192)] 125 | 126 | ### 2017 127 | 128 | * CANE: Context-Aware Network Embedding for Relation Modeling (**ACL**) [[paper](http://nlp.csai.tsinghua.edu.cn/~tcc/publications/acl2017_cane.pdf)][[code](https://github.com/thunlp/CANE)][[slide](http://nlp.csai.tsinghua.edu.cn/~tcc/publications/cane_acl.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/103791236)] 129 | 130 | * Inductive representation learning on large graph (**NeurIPS**) [[paper](https://arxiv.org/pdf/1706.02216.pdf)][[code](https://github.com/williamleif/GraphSAGE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/104122280)] 131 | 132 | * PRISM: Profession Identification in Social Media (**ACM**) [[paper](https://dl.acm.org/doi/pdf/10.1145/3070665)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110469312)] 133 | 134 | * TransNet: Translation-Based NRL for Social Relation Extraction (**IJCAI**) [[paper](http://nlp.csai.tsinghua.edu.cn/~tcc/publications/ijcai2017_transnet.pdf)][[code](https://github.com/thunlp/TransNet)][[slide](http://nlp.csai.tsinghua.edu.cn/~tcc/publications/ijcai2017_transnet_shenzhen.pdf)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110836791)] 135 | 136 | * Learning Community Embedding with Community Detection and Node Embedding on Graphs (**CIKM**) [[paper](http://ww.sentic.net/community-embedding.pdf)][[code](https://github.com/andompesta/ComE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/115056813)] 137 | 138 | ### 2016 139 | 140 | * Asymmetric Transitivity Preserving Graph Embedding (**KDD**) [[paper](https://zw-zhang.github.io/files/2016_KDD_HOPE.pdf)][[code](https://github.com/ZW-ZHANG/HOPE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/103829868)] 141 | 142 | * Structural Deep Network Embedding (**KDD**) [[paper](https://www.kdd.org/kdd2016/subtopic/view/structural-deep-network-embedding)][[code](https://github.com/suanrong/SDNE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/105557064)] 143 | 144 | * node2vec: Scalable Feature Learning for Networks (**KDD**) [[paper](https://arxiv.org/abs/1607.00653)][[code](https://github.com/aditya-grover/node2vec)][[note](https://blog.csdn.net/CSDNTianJi/article/details/109146279)] 145 | 146 | * Max-Margin DeepWalk: Discriminative Learning of Network Representation (**IJCAI**) [[paper](http://nlp.csai.tsinghua.edu.cn/~tcc/publications/ijcai2016_mmdw.pdf)][[code](https://github.com/thunlp/MMDW)][[note](https://blog.csdn.net/CSDNTianJi/article/details/110749863)] 147 | 148 | ### 2015 149 | 150 | * LINE: Large-scale Information Network Embedding (**WWW**) [[paper](https://arxiv.org/pdf/1503.03578.pdf%C2%A0%E3%80%90WWW)][[code](https://github.com/tangjianpku/LINE)][[note](https://blog.csdn.net/CSDNTianJi/article/details/104537980)] 151 | 152 | ### 2014 153 | 154 | * DeepWalk: online learning of social representations (**KDD**) [[paper](https://arxiv.org/pdf/1403.6652.pdf%C3%AF%C2%BC%E2%80%BA)][[code](https://github.com/phanein/deepwalk)][[note](https://blog.csdn.net/CSDNTianJi/article/details/104060366)] 155 | 156 | 157 | 158 | ## Cite Us 159 | 160 | 如果您感觉有所帮助，请引用我们的文章作为鼓励~ 161 | 162 | ```bibtex 163 | @inproceedings{TGC_ML_ICLR, 164 | title={Deep Temporal Graph Clustering}, 165 | author={Liu, Meng and Liu, Yue and Liang, Ke and Tu, Wenxuan and Wang, Siwei and Zhou, Sihang and Liu, Xinwang}, 166 | booktitle={The 12th International Conference on Learning Representations}, 167 | year={2024} 168 | } 169 | 170 | @article{S2T_ML, 171 | title={Self-Supervised Temporal Graph Learning with Temporal and Structural Intensity Alignment}, 172 | author={Liu, Meng and Liang, Ke and Zhao, Yawei and Tu, Wenxuan and Zhou, Sihang and Liu, Xinwang and He Kunlun}, 173 | journal={IEEE Transactions on Neural Networks and Learning Systems}, 174 | year={2024} 175 | } 176 | ``` 177 | --------------------------------------------------------------------------------