Home

Awesome

Deep Learning on Graphs: a roadmap

This roadmap explores the latest advances made in the field of deep learning on graphs. After listing the main papers that set the foundations of DL on graphs and Graph Neural Networks, we dig in various sub-topics. Sub-topics include graph VAE, generative model of graphs, theoretical studies of the expressiveness power of GNNs, edge-informative graphs etc..

I would continue adding papers to this roadmap. Feel free to suggest new papers that are missing in this list.

1. Impactful Graph Neural Networks (chronological order):

[1] M. Defferrard, X. Bresson, and P. Vandergheynst, Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering, NeurIPS, 2016 [pdf] [code TensorFlow]

[2] N. Kipf and M. Welling, Semi supervised classification with graph convolutional networks, 2017, ICLR [pdf][code TensorFlow]

[3] A. Santoro, D. Raposo, D. G. T. Barrett, M. Malinowski, R. Pascanu, P. Battaglia, and T. Lillicrap, A simple neural network module for relational reasoning, NeurIPS, 2017 [pdf] [code PyTorch] [code TensorFlow]

[4] J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl, Neural Message Passing for Quantum Chemistry, ICML, 2017 [pdf]

[5] P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, Graph Attention Networks, ICLR, 2018 [pdf] [code TensorFlow].

2. Literature Reviews

[1] P. W. Battaglia, J. B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner, C. Gulcehre, F. Song, A. Ballard, J. Gilmer, G. Dahl, A. Vaswani, K. Allen, C. Nash, V. Langston, C. Dyer, N. Heess, D. Wierstra, P. Kohli, M. Botvinick, O. Vinyals, Y. Li, and R. Pascanu, Relational inductive biases, deep learning, and graph networks [pdf] [code]

[2] J. Zhou, G. Cui, Z. Zhang, C. Yang, Z. Liu, and M. Sun, Graph Neural Networks: A Review of Methods and Applications [pdf]

[3] Z. Zhang, P. Cui, and W. Zhu, Deep Learning on Graphs: A Survey [pdf]

[4] W. Zonghan, P. Shirui, C. Fengwen, L. Guodong, Z. Chengqi, Y. Philip, A Comprehensive Survey on Graph Neural Networks [pdf]

3. Let's dig by topic:

3.1 GNN for Edge-Informative graphs:

[1] M. Simonovsky and N. Komodakis. Dynamic edge-conditioned filters in convolutional neu- ral networks on graphs, 2017, CVPR.[pdf]

[2] M. Schlichtkrull, T. N. Kipf, P. Bloem, R. van den Berg, I. Titov, M. Welling. Modeling Relational Data with Graph Convolutional Networks, 2018, In Extended Semantic Web Conference. [pdf]

[3] G. Jaume, A. Nguyen, M. Rodriguez, J-P. Thiran, M. Gabrani, edGNN: A simple and powerful GNN for directed labeled graphs, 2019, ICLR workshop on graphs and manifolds. [pdf] [code]

3.2 Unsupervised Graph Neural Networks

[1] Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm, Deep Graph Infomax ICLR 2019 [pdf] [code PyTorch].

[2] Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay S. Pande, Jure Leskovec, Pre-training Graph Neural Networks submitted to NeuIPS 2019 [pdf].

[3] Graph auto-encoder and generative graph modeling. See Section 3.6 & 3.7

3.3 Characterization of Graph Neural Networks

[1] K. Xu, W. Hu, J. Leskovec, S. Jegelka, How Powerful are Graph Neural Networks ?, ICLR, 2019 [pdf] [code PyTorch]

[2] C. Morris, M. Ritzert, M. Fey , W. L. Hamilton, J. Lenssen, G. Rattan, M. Grohe, Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks, AAAI, 2018 [pdf] [code PyTorch]

[3] F. Wu, T. Zhang, A. Holanda de Souza Jr., C. Fifty, T. Yu, K. Q. Weinberger, Simplifying Graph Convolutional Networks, ICML, 2019 [pdf]

[4] H. NT, T. Maehara, Revisiting Graph Neural Networks: All We Have is Low-Pass Filters, submitted to NeurIPS, 2019 [pdf]

[5] N. Dehmamy,A-L Barabási, R. Yu, Understanding the Representation Power of GraphNeural Networks in Learning Graph Topology, NeurIPS, 2019 [pdf]

3.4 Pooling on graphs:

[1] M. Zhang, Z. Cui, M. Neumann, Y. Chen, An End-to-End Deep Learning Architecture for Graph Classification, AAAI, 2018 [pdf]

[2] R. Ying, J. You, C. Morris, X. Ren, W. L. Hamilton, and J. Leskovec, Hierarchical Graph Representation Learning with Differentiable Pooling, 2018, NeurIPS. [pdf] [code]

[3] Anonymous Review, GRAPH U-NET, to be presented at ICLR 2019 [pdf]

[4] J. Lee, I. Lee, J. Kang, Self-Attention Graph Pooling, ICML, 2019 [pdf]

3.5 Relational Reinforcement Learning:

[1] V. Zambaldi, D. Raposo, A. Santoro, V. Bapst, Y. Li, I. Babuschkin, K. Tuyls, D. Reichert, T. Lillicrap, E. Lockhart, M. Shanahan, V. Langston, R. Pascanu, M. Botvinick, O. Vinyals, and P. Battaglia, Relational Deep Reinforcement Learning, 2018 [pdf]

3.6 Generative models of graphs:

[1] J. You, R. Ying, X. Ren, W. L. Hamilton, J. Leskovec, GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models, ICML, 2018 [pdf]

[2] Y. Li, O. Vinyals, C. Dyer, R. Pascanu, P. Battaglia, Learning Deep Generative Models of Graphs, 2018 [pdf]

[3] J. You, B. Liu, R. Ying, V. Pande, and J. Leskovec, Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation, NeurIPS, 2018 [pdf]

[4] M. Simonovsky, N. Komodakis GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders, 2018. [pdf]

[5] W. Jin, R. Barzilay, T. Jaakkola, Junction Tree Variational Autoencoder for Molecular Graph Generation, ICML, 2018. [pdf] [code PyTorch]

[6] N. De Cao and T. Kipf, MolGAN: An implicit generative model for small molecular graphs, 2018 [pdf]

[7] Q. Liu, M. Allamanis, M. Brockschmidt, A. L. Gaunt Constrained Graph Variational Autoencoders for Molecule Design, NeuIPS, 2018. [pdf]

[8] A. Grover, A. Zweig, S. Ermon, Graphite: Iterative Generative Modeling of Graphs, ICML, 2019. [pdf] [code TensorFlow]

[9] C. Yang, P. Zhuang, W. Shi, A. Luu, P. Li, Conditional Structure Generation through Graph Variational Generative Adversarial Nets, NeurIPS, 2019. [pdf] [code PyTorch]

[10] R. Liao, Y. Li, Y. Song, S. Wang, C. Nash, W. L. Hamilton, D. Duvenaud, R. Urtasun, R. S. Zemel, Efficient Graph Generation with Graph Recurrent Attention Networks, NeurIPS, 2019. [pdf] [code PyTorch]

3.7 Graph Autoencoders

[1] T. N. Kipf and M. Welling., Variational graph auto-encoders, 2016, Bayesian DL, NeurIPS [pdf]

[2] T. N. Kipf, E. Fetaya, K. Wang, M. Welling, R. Zemel, Neural Relational Inference for Interacting Systems, ICML, 2018 [pdf]

3.8 Scene Understanding (e.g., Scene Graph Generation)

[1] D. Xu, Y. Zhu, C. B. Choy, and L. Fei-Fei. Scene graph generation by iterative message passing, CVPR,2017. [pdf]

[2] J. Yang, J. Lu, S. Lee, D. Batra, and D. Parikh. Graph R-CNN for Scene Graph Generation, ECCV, 2018. [pdf]

[3] G. Jaume, B. Bozorgtabar, H. Ekenel, J-P. Thiran, M. Gabrani, Image-Level Attentional Context Modeling using Nest Graph Neural Networks, NeuIPS workshop on Relational Representation Learning [pdf]

3.9 Knowledge Graphs

[1] M. Nickel, K. Murphy, V. Tresp, E. Gabrilovich, A Review of Relational Machine Learning for Knowledge Graphs 2015 [pdf]

3.10 Neural Architecture Search with GNNs

[1] C. Zhang, M. Ren, R. Urtasun, Graph Hyper Networks for Neural Architecture Search, ICLR 2019 [pdf]

3.xx More to come

4. Libraries

5. Presentation/Slides

6. Videos

7. Workshops