Github上的图神经网络必读论文和最新进展列表（附链接）

来源：专知

本文共2517字，建议阅读7分钟。

本文为你分享图神经网络的必读论文和最新进展列表。

[ 导读 ]近两年来，图神经网络的飞速发展，在自然语言处理、计算机视觉、推荐系统、信息检索等领域都引起了许多研究者的关注。在最新的人工智能相关热门会议中，如NIPS、CVPR、MM等，几乎总能找到几篇和图神经网络相关的论文。本文介绍Github上的一个图神经网络必读论文和最新进展列表。

许多重要的真实应用和问题都可以用图的形式建模，例如社交网络、脑网络、3D点云等。由于交叉学科研究的驱动等原因，图数据上的神经网络已经成为研究的热点之一。Github项目jdlc105/Must-read-papers-and-continuous-tracking-on-Graph-Neural-Network-GNN-progress聚焦于图神经网络（GNN），列出了相关的必读论文和最新的进展。该项目正在等待CVPR 2019, WWW2019, SIGKDD2019, ICML2019等会议放出最新的GNN相关论文。

该项目目录如下：

• 综述

• 期刊论文

• 会议论文

• ARXIV论文

• 开源平台

具体内容如下：

综述

---

1. Ziwei Zhang, Peng Cui, Wenwu Zhu, Deep Learning on Graphs: A Survey, ArXiv, 2018.

2. Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Maosong Sun, Graph Neural Networks: A Review of Methods and Applications, ArXiv, 2018. 

3. Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu(Fellow,IEEE), A Comprehensive Survey on Graph Neural Networks, ArXiv, 2019. 

期刊论文

---

1. F. Scarselli, M. Gori, A.C. Tsoi, M. Hagenbuchner, G. Monfardini, The graph neural network model, IEEE Transactions on Neural Networks(IEEE Transactions on Neural Networks and Learning Systems), 2009. 

2. Scarselli F, Gori M, Tsoi A C, et al. Computational capabilities of graph neural networks, IEEE Transactions on Neural Networks, 2009.

3. Micheli A . Neural Network for Graphs: A Contextual Constructive Approach. IEEE Transactions on Neural Networks, 2009. 

4. Goles, Eric, and Gonzalo A. Ruz. Dynamics of Neural Networks over Undirected Graphs. Neural Networks, 2015. 

5. Z. Luo, L. Liu, J. Yin, Y. Li, Z. Wu, Deep Learning of Graphs with Ngram Convolutional Neural Networks, IEEE Transactions on Knowledge & Data Engineering, 2017. 

6. Petroski Such F , Sah S , Dominguez M A , et al. Robust Spatial Filtering with Graph Convolutional Neural Networks. IEEE Journal of Selected Topics in Signal Processing, 2017. 

7. Kawahara J, Brown C J, Miller S P, et al. BrainNetCNN: convolutional neural networks for brain networks; towards predicting neurodevelopment. NeuroImage, 2017. 

8. Muscoloni A , Thomas J M , Ciucci S , et al. Machine learning meets complex networks via coalescent embedding in the hyperbolic space. Nature Communications, 2017. 

9. D.M. Camacho, K.M. Collins, R.K. Powers, J.C. Costello, J.J. Collins, Next-Generation Machine Learning for Biological Networks, Cell, 2018. 

10. Marinka Z , Monica A , Jure L . Modeling polypharmacy side effects with graph convolutional networks. Bioinformatics, 2018. 

11. Sarah P , Ira K S , Enzo F , et al. Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer’s Disease. Medical Image Analysis, 2018. 

12. Sofia Ira Ktena, Sarah Parisot, Enzo Ferrante, Martin Rajchl, Matthew Lee, Ben Glocker, Daniel Rueckert, Metric learning with spectral graph convolutions on brain connectivity networks, NeuroImage, 2018. 

13. Xie T , Grossman J C . Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. Physical Review Letters, 2018. 

14. Phan, Anh Viet, Minh Le Nguyen, Yen Lam Hoang Nguyen, and Lam Thu Bui. DGCNN: A Convolutional Neural Network over Large-Scale Labeled Graphs. Neural Networks, 2018.

15. Song T, Zheng W, Song P, et al. Eeg emotion recognition using dynamical graph convolutional neural networks. IEEE Transactions on Affective Computing, 2018.

16. Levie R, Monti F, Bresson X, et al. Cayleynets: Graph convolutional neural networks with complex rational spectral filters. IEEE Transactions on Signal Processing 2019.

17. Zhang, Zhihong, Dongdong Chen, Jianjia Wang, Lu Bai, and Edwin R. Hancock. Quantum-Based Subgraph Convolutional Neural Networks. Pattern Recognition, 2019. 

18. Qin A, Shang Z, Tian J, et al. Spectral–Spatial Graph Convolutional Networks for Semisupervised Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, 2019. 

19. Coley C W, Jin W, Rogers L, et al. A graph-convolutional neural network model for the prediction of chemical reactivity. Chemical Science, 2019. 

20. Zhang Z, Chen D, Wang Z, et al. Depth-based Subgraph Convolutional Auto-Encoder for Network Representation Learning. Pattern Recognition, 2019. 

21. Hong Y, Kim J, Chen G, et al. Longitudinal Prediction of Infant Diffusion MRI Data via Graph Convolutional Adversarial Networks. IEEE transactions on medical imaging, 2019. 

22. Khodayar M, Mohammadi S, Khodayar M E, et al. Convolutional Graph Autoencoder: A Generative Deep Neural Network for Probabilistic Spatio-temporal Solar Irradiance Forecasting. IEEE Transactions on Sustainable Energy, 2019. 

会议论文

---

1. Duvenaud D, Maclaurin D, Aguilera-Iparraguirre J, et al. Convolutional networks on graphs for learning molecular fingerprints, NeurIPS(NIPS) 2015. 

2. M. Niepert, M. Ahmed, K. Kutzkov, Learning Convolutional Neural Networks for Graphs, ICML 2016. 

3. S. Cao, W. Lu, Q. Xu, Deep neural networks for learning graph representations, AAAI 2016. 

4. M. Defferrard, X. Bresson, P. Vandergheynst, Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering, NeurIPS(NIPS) 2016. 

5. T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, ICLR 2017. 

6. A. Fout, B. Shariat, J. Byrd, A. Benhur, Protein Interface Prediction using Graph Convolutional Networks, NeurIPS(NIPS) 2017. 

7. Monti F, Bronstein M, Bresson X. Geometric matrix completion with recurrent multi-graph neural networks, NeurIPS(NIPS) 2017. 

8. Simonovsky M, Komodakis N. Dynamic edgeconditioned filters in convolutional neural networks on graphs, CVPR. 2017.

9. R. Li, S. Wang, F. Zhu, J. Huang, Adaptive Graph Convolutional Neural Networks, AAAI 2018.

10. J. You, B. Liu, R. Ying, V. Pande, J. Leskovec, Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation, NeurIPS(NIPS) 2018. 

11. C. Zhuang, Q. Ma, Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification, WWW 2018.

12. H. Gao, Z. Wang, S. Ji, Large-Scale Learnable Graph Convolutional Networks, KDD 2018.

13. D. Zügner, A. Akbarnejad, S. Günnemann, Adversarial Attacks on Neural Networks for Graph Data, KDD 2018.

14. Ying R , He R , Chen K , et al. Graph Convolutional Neural Networks for Web-Scale Recommender Systems. KDD 2018.

15. P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, Y. Bengio, Graph Attention Networks, ICLR, 2018.

16. Beck, Daniel Edward Robert, Gholamreza Haffari and Trevor Cohn. Graph-to-Sequence Learning using Gated Graph Neural Networks. ACL 2018.

17. Marcheggiani D , Bastings J , Titov I . Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks. NAACL 2018.

18. Chen J , Zhu J , Song L . Stochastic Training of Graph Convolutional Networks with Variance Reduction. ICML 2018.

19. Gusi Te, Wei Hu, Amin Zheng, Zongming Guo, RGCNN: Regularized Graph CNN for Point Cloud Segmentation. ACM Multimedia 2018. 

20. Talukdar, Partha, Shikhar Vashishth, Shib Sankar Dasgupta and Swayambhu Nath Ray. Dating Documents using Graph Convolution Networks. ACL 2018. 

21. Sanchez-Gonzalez A , Heess N , Springenberg J T , et al. Graph networks as learnable physics engines for inference and control. ICML 2018.

22. Muhan Zhang, Yixin Chen. Link Prediction Based on Graph Neural Networks. NeurIPS(NIPS) 2018.

23. Chen, Jie, Tengfei Ma, and Cao Xiao. FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling. ICLR 2018.

24. Zhang, Zhen, Hongxia Yang, Jiajun Bu, Sheng Zhou, Pinggang Yu, Jianwei Zhang, Martin Ester, and Can Wang. ANRL: Attributed Network Representation Learning via Deep Neural Networks. IJCAI 2018.

25. Rahimi A , Cohn T , Baldwin T . Semi-supervised User Geolocation via Graph Convolutional Networks. ACL 2018.

26. Morris C , Ritzert M , Fey M , et al.Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks.. AAAI 2019.

27. Xu K, Hu W, Leskovec J, et al. How Powerful are Graph Neural Networks?, ICLR 2019.

28. Johannes Klicpera, Aleksandar Bojchevski, Stephan Günnemann. Combining Neural Networks with Personalized PageRank for Classification on Graphs, ICLR 2019.

29. Daniel Zügner, Stephan Günnemann. Adversarial Attacks on Graph Neural Networks via Meta Learning, ICLR 2019.

30. Zhang Xinyi, Lihui Chen. Capsule Graph Neural Network, ICLR 2019.

31. Liao, R., Zhao, Z., Urtasun, R., and Zemel, R. LanczosNet: Multi-Scale Deep Graph Convolutional Networks, ICLR 2019.

32. Bingbing Xu, Huawei Shen, Qi Cao, Yunqi Qiu, Xueqi Cheng. Graph Wavelet Neural Network, ICLR 2019.

33. Hu J, Guo C, Yang B, et al. Stochastic Weight Completion for Road Networks using Graph Convolutional Networks,ICDE. 2019.

34. Yao L, Mao C, Luo Y . Graph Convolutional Networks for Text Classification. AAAI 2019.

35. Landrieu L , Boussaha M . Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning. CVPR 2019.

36. Si C , Chen W , Wang W , et al. An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition. CVPR 2019.

37. Cucurull G , Taslakian P , Vazquez D . Context-Aware Visual Compatibility Prediction. CVPR 2019.

38. Jia-Xing Zhong, Nannan Li, Weijie Kong, Shan Liu, Thomas H. Li, Ge Li. Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection. CVPR 2019.

39. Michael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing. Rethinking Knowledge Graph Propagation for Zero-Shot Learning. CVPR 2019.

40. Arushi Goel, Keng Teck Ma, Cheston Tan. An End-to-End Network for Generating Social Relationship Graphs. CVPR 2019.

41. Yichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang. Learning Context Graph for Person Search. CVPR 2019.

42. Zhongdao Wang, Liang Zheng, Yali Li, Shengjin Wang. Linkage Based Face Clustering via Graph Convolution Network. CVPR 2019

43. Lei Yang, Xiaohang Zhan, Dapeng Chen, Junjie Yan, Chen Change Loy, Dahua Lin. Learning to Cluster Faces on an Affinity Graph. CVPR 2019

44. Yao Ma, Suhang Wang, Charu C. Aggarwal, Jiliang Tang. Graph Convolutional Networks with EigenPooling. KDD2019.

45. Wenqi Fan, Yao Ma, Qing Li, Yuan He, Eric Zhao, Jiliang Tang, Dawei Yin. Graph Neural Networks for Social Recommendation. WWW2019,

46. Kim J, Kim T, Kim S, et al. Edge-labeling Graph Neural Network for Few-shot Learning. CVPR 2019.

47. Jessica V. Schrouff, Kai Wohlfahrt, Bruno Marnette, Liam Atkinson. INFERRING JAVASCRIPT TYPES USING GRAPH NEURAL NETWORKS. ICLR 2019.

48. Emanuele Rossi, Federico Monti, Michael Bronstein, Pietro liò. ncRNA Classification with Graph Convolutional Networks. SIGKDD 2019.

49. Wu F, Zhang T, Souza Jr A H, et al. Simplifying Graph Convolutional Networks. ICML 2019. 

50. Junhyun Lee, Inyeop Lee, Jaewoo Kang. Self-Attention Graph Pooling. ICML 2019. 

ARXIV论文

---

1. Li Y, Tarlow D, Brockschmidt M, et al. Gated graph sequence neural networks. arXiv 2015.

2. Henaff M, Bruna J, LeCun Y. Deep convolutional networks on graph-structured data, arXiv 2015.

3. Hechtlinger Y, Chakravarti P, Qin J. A generalization of convolutional neural networks to graph-structured data. arXiv 2017.

4. Marcheggiani D, Titov I. Encoding sentences with graph convolutional networks for semantic role labeling. arXiv 2017.

5. Battaglia P W, Hamrick J B, Bapst V, et al. Relational inductive biases, deep learning, and graph networks, arXiv 2018.

6. Verma S, Zhang Z L. Graph Capsule Convolutional Neural Networks. arXiv 2018.

7. Zhang T , Zheng W , Cui Z , et al. Tensor graph convolutional neural network. arXiv 2018.

8. Zou D, Lerman G. Graph Convolutional Neural Networks via Scattering. arXiv 2018.

9. Du J , Zhang S , Wu G , et al. Topology Adaptive Graph Convolutional Networks. arXiv 2018. 

10. Shang C , Liu Q , Chen K S , et al. Edge Attention-based Multi-Relational Graph Convolutional Networks. arXiv 2018. 

11. Scardapane S , Vaerenbergh S V , Comminiello D , et al. Improving Graph Convolutional Networks with Non-Parametric Activation Functions. arXiv 2018. 

12. Wang Y , Sun Y , Liu Z , et al. Dynamic Graph CNN for Learning on Point Clouds. arXiv 2018. 

13. Ryu S , Lim J , Hong S H , et al. Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network. arXiv 2018. 

14. Cui Z , Henrickson K , Ke R , et al. High-Order Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. arXiv 2018. 

15. Shchur O , Mumme M , Bojchevski A , et al. Pitfalls of Graph Neural Network Evaluation. arXiv 2018. 

16. Bai Y , Ding H , Bian S , et al. Graph Edit Distance Computation via Graph Neural Networks. arXiv 2018. 

17. Pedro H. C. Avelar, Henrique Lemos, Marcelo O. R. Prates, Luis Lamb, Multitask Learning on Graph Neural Networks - Learning Multiple Graph Centrality Measures with a Unified Network. arXiv 2018. 

18. Matthew Baron, Topology and Prediction Focused Research on Graph Convolutional Neural Networks. arXiv 2018. 

19. Wenting Zhao, Chunyan Xu, Zhen Cui, Tong Zhang, Jiatao Jiang, Zhenyu Zhang, Jian Yang, When Work Matters: Transforming Classical Network Structures to Graph CNN. arXiv 2018. 

20. Xavier Bresson, Thomas Laurent, Residual Gated Graph ConvNets. arXiv 2018. 

21. Kun XuLingfei WuZhiguo WangYansong FengVadim Sheinin, Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks. arXiv 2018. 

22. Xiaojie GuoLingfei WuLiang Zhao. Deep Graph Translation. arXiv 2018. 

23. Choma, Nicholas, et al. Graph Neural Networks for IceCube Signal Classification. ArXiv 2018. 

24. Tyler Derr, Yao Ma, Jiliang Tang. Signed Graph Convolutional Network ArXiv 2018. 

25. Yawei Luo, Tao Guan, Junqing Yu, Ping Liu, Yi Yang. Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning ArXiv 2018. 

26. Sun K, Koniusz P, Wang J. Fisher-Bures Adversary Graph Convolutional Networks. arXiv 2019. 

27. Kazi A, Burwinkel H, Vivar G, et al. InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Prediction. arXiv 2019. 

28. Lemos H, Prates M, Avelar P, et al. Graph Colouring Meets Deep Learning: Effective Graph Neural Network Models for Combinatorial Problems. arXiv 2019. 

29. Diehl F, Brunner T, Le M T, et al. Graph Neural Networks for Modelling Traffic Participant Interaction. arXiv 2019. 

30. Murphy R L, Srinivasan B, Rao V, et al. Relational Pooling for Graph Representations. arXiv 2019. 

31. Zhang W, Shu K, Liu H, et al. Graph Neural Networks for User Identity Linkage. arXiv 2019. 

32. Ruiz L, Gama F, Ribeiro A. Gated Graph Convolutional Recurrent Neural Networks. arXiv 2019. 

33. Phillips S, Daniilidis K. All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks. arXiv 2019. 

34. Hu F, Zhu Y, Wu S, et al. Semi-supervised Node Classification via Hierarchical Graph Convolutional Networks. arXiv 2019. 

35. Deng Z, Dong Y, Zhu J. Batch Virtual Adversarial Training for Graph Convolutional Networks. arXiv 2019. 

36. Chen Z M, Wei X S, Wang P, et al.Multi-Label Image Recognition with Graph Convolutional Networks. arXiv 2019. 

37. Mallea M D G, Meltzer P, Bentley P J. Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations. arXiv 2019. 

38. Peter Meltzer, Marcelo Daniel Gutierrez Mallea and Peter J. Bentley. PiNet: A Permutation Invariant Graph Neural Network for Graph Classification. arXiv 2019. 

39. Padraig Corcoran. Function Space Pooling For Graph Convolutional Networks. arXiv 2019. 

开源平台

1. Deep Graph Library（DGL)
   

    https://github.com/jermainewang/dgl

2. NGra

3. Graph_nets
   

   https://github.com/deepmind/graph_nets

4. Euler
   

   https://github.com/alibaba/euler

5. PyTorch Geometric

   https://github.com/rusty1s/pytorch_geometric

6. PyTorch-BigGraph（PBG）
   

   https://github.com/facebookresearch/PyTorch-BigGraph

参考链接：

• https://github.com/jdlc105/Must-read-papers-and-continuous-tracking-on-Graph-Neural-Network-GNN-progress/blob/master/README.md

编辑：文婧