GNN Papers.md

Graph Networks Related Work

Survey

1. A Comprehensive Survey on Graph Neural Networks, 2019. [paper]
2. Graph Neural Networks: A Review of Methods and Applications, 2019. [paper]

Theory and Models

1. Relational inductive biases, deep learning, and graph networks, 2018. [paper]
2. Unsupervised Learning of Latent Physical Properties Using Perception-Prediction Networks, 2018. [paper]
3. Interaction Networks for Learning about Objects, Relations and Physics, 2016. [paper]
4. Neural Relational Inference for Interacting Systems, 2018. [paper]
5. Factorised Neural Relational Inference for Multi-Interaction Systems, 2019. [paper]
6. Graph networks as learnable physics engines for inference and control, 2018. [paper]
7. Relational Forward Models for Multi-Agent Learning, 2018. [paper]
8. VAIN: Attentional Multi-agent Predictive Modeling, 2018. [paper]
9. Graph Attention Networks, 2018. [paper]
10. Neural Message Passing for Quantum Chemistry, 2017. [paper]
11. Deep Sets, 2018. [paper]
12. How Powerful are Graph Neural Networks?, 2019. [paper]

Applications

1. Diverse Generation for Multi-agent Sports Games, CVPR 2019. [paper]
2. Generative Modeling of Multimodal Multi-Human Behavior, IROS 2018. [paper]
3. Stochastic Prediction of Multi-Agent Interactions from Partial Observations, 2019. [paper]
4. GRIP: Graph-based Interaction-aware Trajectory Prediction, 2019. [paper]
5. TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents, 2018. [paper]
6. Stochastic trajectory prediction with social graph network, 2019. [paper]
7. DROGON: A Causal Reasoning Framework for Future Trajectory Forecast, 2019. [paper]
8. Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks, 2019. [paper]
9. The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic Spatiotemporal Graphs, 2019. [paper]
10. Relational Deep Reinforcement Learning, 2018. [paper]
11. MolGAN: An implicit generative model for small molecular graphs, 2018. [paper]