Timezone: »
This paper builds on the connection between graph neural networks and traditional dynamical systems. We propose continuous graph neural networks (CGNN), which generalise existing graph neural networks with discrete dynamics in that they can be viewed as a specific discretisation scheme. The key idea is how to characterise the continuous dynamics of node representations, i.e. the derivatives of node representations, w.r.t. time.Inspired by existing diffusion-based methods on graphs (e.g. PageRank and epidemic models on social networks), we define the derivatives as a combination of the current node representations,the representations of neighbors, and the initial values of the nodes. We propose and analyse two possible dynamics on graphs—including each dimension of node representations (a.k.a. the feature channel) change independently or interact with each other—both with theoretical justification. The proposed continuous graph neural net-works are robust to over-smoothing and hence allow us to build deeper networks, which in turn are able to capture the long-range dependencies between nodes. Experimental results on the task of node classification demonstrate the effectiveness of our proposed approach over competitive baselines.
Author Information
Louis-Pascal Xhonneux (Mila / Université de Montréal)
Meng Qu (Mila)
Jian Tang (HEC Montreal & MILA)
More from the Same Authors
-
2023 : A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs »
Zhaocheng Zhu · Xinyu Yuan · Mikhail Galkin · Louis-Pascal Xhonneux · Ming Zhang · Maxime Gazeau · Jian Tang -
2022 Poster: Neural-Symbolic Models for Logical Queries on Knowledge Graphs »
Zhaocheng Zhu · Mikhail Galkin · Zuobai Zhang · Jian Tang -
2022 Spotlight: Neural-Symbolic Models for Logical Queries on Knowledge Graphs »
Zhaocheng Zhu · Mikhail Galkin · Zuobai Zhang · Jian Tang -
2021 Poster: Self-supervised Graph-level Representation Learning with Local and Global Structure »
Minghao Xu · Hang Wang · Bingbing Ni · Hongyu Guo · Jian Tang -
2021 Spotlight: Self-supervised Graph-level Representation Learning with Local and Global Structure »
Minghao Xu · Hang Wang · Bingbing Ni · Hongyu Guo · Jian Tang -
2021 Poster: Learning Gradient Fields for Molecular Conformation Generation »
Chence Shi · Shitong Luo · Minkai Xu · Jian Tang -
2021 Poster: An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming »
Minkai Xu · Wujie Wang · Shitong Luo · Chence Shi · Yoshua Bengio · Rafael Gomez-Bombarelli · Jian Tang -
2021 Poster: Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction »
Hangrui Bi · Hengyi Wang · Chence Shi · Connor Coley · Jian Tang · Hongyu Guo -
2021 Spotlight: Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction »
Hangrui Bi · Hengyi Wang · Chence Shi · Connor Coley · Jian Tang · Hongyu Guo -
2021 Spotlight: An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming »
Minkai Xu · Wujie Wang · Shitong Luo · Chence Shi · Yoshua Bengio · Rafael Gomez-Bombarelli · Jian Tang -
2021 Oral: Learning Gradient Fields for Molecular Conformation Generation »
Chence Shi · Shitong Luo · Minkai Xu · Jian Tang -
2020 Workshop: Bridge Between Perception and Reasoning: Graph Neural Networks & Beyond »
Jian Tang · Le Song · Jure Leskovec · Renjie Liao · Yujia Li · Sanja Fidler · Richard Zemel · Ruslan Salakhutdinov -
2020 : Opening Remarks: Jian Tang & Le Song »
Jian Tang · Le Song -
2020 Poster: A Graph to Graphs Framework for Retrosynthesis Prediction »
Chence Shi · Minkai Xu · Hongyu Guo · Ming Zhang · Jian Tang -
2020 Poster: Learning to Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning »
Sai Krishna Gottipati · Boris Sattarov · Sufeng Niu · Yashaswi Pathak · Haoran Wei · Shengchao Liu · Shengchao Liu · Simon Blackburn · Karam Thomas · Connor Coley · Jian Tang · Sarath Chandar · Yoshua Bengio -
2020 Poster: Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs »
Meng Qu · Tianyu Gao · Louis-Pascal Xhonneux · Jian Tang -
2019 Poster: GMNN: Graph Markov Neural Networks »
Meng Qu · Yoshua Bengio · Jian Tang -
2019 Oral: GMNN: Graph Markov Neural Networks »
Meng Qu · Yoshua Bengio · Jian Tang