Must-read papers on GNN

GNN: graph neural network

Contributed by Jie Zhou, Ganqu Cui, Zhengyan Zhang and Yushi Bai.

Content

<table> <tr><td colspan="2"><a href="#survey-papers">1. Survey</a></td></tr> <tr><td colspan="2"><a href="#models">2. Models</a></td></tr> <tr> <td>&ensp;<a href="#basic-models">2.1 Basic Models</a></td> <td>&ensp;<a href="#graph-types">2.2 Graph Types</a></td> </tr> <tr> <td>&ensp;<a href="#pooling-methods">2.3 Pooling Methods</a></td> <td>&ensp;<a href="#analysis">2.4 Analysis</a></td> </tr> <tr> <td>&ensp;<a href="#efficiency">2.5 Efficiency</a></td> <td>&ensp;<a href="#explainability">2.6 Explainability</a></td> </tr> <tr><td colspan="2"><a href="#applications">3. Applications</a></td></tr> <tr> <td>&ensp;<a href="#physics">3.1 Physics</a></td> <td>&ensp;<a href="#chemistry-and-biology">3.2 Chemistry and Biology</a></td> </tr> <tr> <td>&ensp;<a href="#knowledge-graph">3.3 Knowledge Graph</a></td> <td>&ensp;<a href="#recommender-systems">3.4 Recommender Systems</a></td> </tr> <tr> <td>&ensp;<a href="#computer-vision">3.5 Computer Vision</a></td> <td>&ensp;<a href="#natural-language-processing">3.6 Natural Language Processing</a></td> </tr> <tr> <td>&ensp;<a href="#generation">3.7 Generation</a></td> <td>&ensp;<a href="#combinatorial-optimization">3.8 Combinatorial Optimization</a></td> </tr> <tr> <td>&ensp;<a href="#adversarial-attack">3.9 Adversarial Attack</a></td> <td>&ensp;<a href="#graph-clustering">3.10 Graph Clustering</a></td> </tr> <tr> <td>&ensp;<a href="#graph-classification">3.11 Graph Classification</a></td> <td>&ensp;<a href="#reinforcement-learning">3.12 Reinforcement Learning</a></td> </tr> <tr> <td>&ensp;<a href="#traffic-network">3.13 Traffic Network</a></td> <td>&ensp;<a href="#few-shot-and-zero-shot-learning">3.14 Few-shot and Zero-shot Learning</a></td> </tr> <tr> <td>&ensp;<a href="#program-representation">3.15 Program Representation</a></td> <td>&ensp;<a href="#social-network">3.16 Social Network</a></td> </tr> <tr> <td>&ensp;<a href="#graph-matching">3.17 Graph Matching</a></td> <td>&ensp;<a href="#computer-network">3.18 Computer Network</a></td> </tr> </table>

Survey papers

1. Introduction to Graph Neural Networks. Synthesis Lectures on Artificial Intelligence and Machine Learning, Morgan & Claypool Publishers, 2020. book

   Zhiyuan Liu, Jie Zhou.

2. Graph Neural Networks: A Review of Methods and Applications. AI Open 2020. paper

   Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Maosong Sun.

3. A Comprehensive Survey on Graph Neural Networks. arxiv 2019. paper

   Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, Philip S. Yu.

4. Adversarial Attack and Defense on Graph Data: A Survey. arxiv 2018. paper

   Lichao Sun, Yingtong Dou, Carl Yang, Ji Wang, Philip S. Yu, Bo Li.

5. Deep Learning on Graphs: A Survey. arxiv 2018. paper

   Ziwei Zhang, Peng Cui, Wenwu Zhu.

6. Relational Inductive Biases, Deep Learning, and Graph Networks. arxiv 2018. paper

   Battaglia, Peter W and Hamrick, Jessica B and Bapst, Victor and Sanchez-Gonzalez, Alvaro and Zambaldi, Vinicius and Malinowski, Mateusz and Tacchetti, Andrea and Raposo, David and Santoro, Adam and Faulkner, Ryan and others.

7. Geometric Deep Learning: Going beyond Euclidean data. IEEE SPM 2017. paper

   Bronstein, Michael M and Bruna, Joan and LeCun, Yann and Szlam, Arthur and Vandergheynst, Pierre.

8. Computational Capabilities of Graph Neural Networks. IEEE TNN 2009. paper

   Scarselli, Franco and Gori, Marco and Tsoi, Ah Chung and Hagenbuchner, Markus and Monfardini, Gabriele.

9. Neural Message Passing for Quantum Chemistry. ICML 2017. paper

   Gilmer, Justin and Schoenholz, Samuel S and Riley, Patrick F and Vinyals, Oriol and Dahl, George E.

10. Non-local Neural Networks. CVPR 2018. paper

    Wang, Xiaolong and Girshick, Ross and Gupta, Abhinav and He, Kaiming.

11. The Graph Neural Network Model. IEEE TNN 2009. paper

    Scarselli, Franco and Gori, Marco and Tsoi, Ah Chung and Hagenbuchner, Markus and Monfardini, Gabriele.

12. Benchmarking Graph Neural Networks. arxiv 2020. paper

    Dwivedi, Vijay Prakash and Joshi, Chaitanya K. and Laurent, Thomas and Bengio, Yoshua and Bresson, Xavier.

13. Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey. arxiv 2020. paper

    Skarding, Joakim and Gabrys, Bogdan and Musial, Katarzyna.

14. Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks. arxiv 2020. paper

    Zhiqian Chen, Fanglan Chen, Lei Zhang, Taoran Ji, Kaiqun Fu, Liang Zhao, Feng Chen, Chang-Tien Lu.

15. Explainability in Graph Neural Networks: A Taxonomic Survey. arxiv 2020. paper

    Hao Yuan, Haiyang Yu, Shurui Gui, Shuiwang Ji.

16. Self-Supervised Learning of Graph Neural Networks: A unified view. TPAMI 2022. paper

    Yaochen Xie, Zhao Xu, Jingtun Zhang, Zhangyang Wang, Shuiwang Ji.

Models

Basic Models

1. Supervised Neural Networks for the Classification of Structures. IEEE TNN 1997. paper

   Alessandro Sperduti and Antonina Starita.

2. Graphical-Based Learning Environments for Pattern Recognition. SSPR/SPR 2004. paper

   Franco Scarselli, Ah Chung Tsoi, Marco Gori, Markus Hagenbuchner.

3. A new model for learning in graph domains. IJCNN 2005. paper

   Marco Gori, Gabriele Monfardini, Franco Scarselli.

4. Graph Neural Networks for Ranking Web Pages. WI 2005. paper

   Franco Scarselli, Sweah Liang Yong, Marco Gori, Markus Hagenbuchner, Ah Chung Tsoi, Marco Maggini.

5. Automatic Generation of Complementary Descriptors with Molecular Graph Networks. J.Chem.Inf.Model. 2005. paper

   Christian Merkwirth and Thomas Lengauer.

6. Neural Network for Graphs: A Contextual Constructive Approach. IEEE TNN 2009. paper

   Alessio Micheli.

7. Spectral Networks and Locally Connected Networks on Graphs. ICLR 2014. paper

   Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun.

8. Deep Convolutional Networks on Graph-Structured Data. arxiv 2015. paper

   Mikael Henaff, Joan Bruna, Yann LeCun.

9. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering. NIPS 2016. paper

   Michaël Defferrard, Xavier Bresson, Pierre Vandergheynst.

10. Diffusion-Convolutional Neural Networks. NIPS 2016. paper

    James Atwood, Don Towsley.

11. Gated Graph Sequence Neural Networks. ICLR 2016. paper

    Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel.

12. Learning Convolutional Neural Networks for Graphs. ICML 2016. paper

    Mathias Niepert, Mohamed Ahmed, Konstantin Kutzkov.

13. Semantic Object Parsing with Graph LSTM. ECCV 2016. paper

    Xiaodan Liang, Xiaohui Shen, Jiashi Feng, Liang Lin, Shuicheng Yan.

14. Semi-Supervised Classification with Graph Convolutional Networks. ICLR 2017. paper

    Thomas N. Kipf, Max Welling.

15. Inductive Representation Learning on Large Graphs. NIPS 2017. paper

    William L. Hamilton, Rex Ying, Jure Leskovec.

16. Geometric deep learning on graphs and manifolds using mixture model cnns. CVPR 2017. paper

    Federico Monti, Davide Boscaini, Jonathan Masci, Emanuele Rodolà, Jan Svoboda, Michael M. Bronstein.

17. Graph Attention Networks. ICLR 2018. paper

    Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, Yoshua Bengio.

18. Covariant Compositional Networks For Learning Graphs. ICLR 2018. paper

    Risi Kondor, Hy Truong Son, Horace Pan, Brandon Anderson, Shubhendu Trivedi.

19. **Graph Partition Neural Networks for Semi-Supervised