Continuous-Depth Neural Models for Dynamic Graph Prediction

Abstract

We introduce the framework of continuous-depth graph neural networks (GNNs). Neural graph differential equations (Neural GDEs) are formalized as the counterpart to GNNs where the input-output relationship is determined by a continuum of GNN layers, blending discrete topological structures and differential equations. The proposed framework is shown to be compatible with static GNN models and is extended to dynamic and stochastic settings through hybrid dynamical system theory. Here, Neural GDEs improve performance by exploiting the underlying dynamics geometry, further introducing the ability to accommodate irregularly sampled data. Results prove the effectiveness of the proposed models across applications, such as traffic forecasting or prediction in genetic regulatory networks.

Extended version of the workshop paper "Graph Neural Ordinary Differential Equations". arXiv admin note: substantial text overlap with arXiv:1911.07532

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Discrete Signal Processing on Graphs
• Simplifying Graph Convolutional Networks
• Latent ODEs for Irregularly-Sampled Time Series
• Recurrent Neural Networks for Time Series Forecasting
• Hamiltonian Graph Networks with ODE Integrators
• Neural Manifold Ordinary Differential Equations
• G2SAT: Learning to Generate SAT Formulas
• TorchDyn: A Neural Differential Equations Library