Graph Neural Ordinary Differential Equations

Michael Poli, Stefano Massaroli, Junyoung Park, Atsushi Yamashita, Hajime Asama +1 more
11/18/2019
cs.LGcs.AIstat.ML

Official code: Zymrael/gde (213 stars, MIT, last commit 2021-04-15).

Abstract

We introduce the framework of continuous--depth graph neural networks (GNNs). Graph neural ordinary differential equations (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 various static and autoregressive GNN models. Results prove general effectiveness of GDEs: in static settings they offer computational advantages by incorporating numerical methods in their forward pass; in dynamic settings, on the other hand, they are shown to improve performance by exploiting the geometry of the underlying dynamics.

View on arXivView PDF

Code Implementations(1)

Zymrael/gdeOfficial100%
MIT

Neural Graph Differential Equations (Neural GDEs)

21334Python, Jupyter NotebookNov 12, 20195 years agoMIT
dynamical-systemsgraph-neural-networksneural-ode

Similar Papers

On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks

87% match2025

Continuous-in-Depth Neural Networks

86% match1 repo412020

Neural Ordinary Differential Equations

85% match1 repo6.5k2018

Signed Graph Neural Ordinary Differential Equation for Modeling Continuous-time Dynamics

85% match1 repo62023

Differential Equations for Continuous-Time Deep Learning

83% match2024

Graph ODEs and Beyond: A Comprehensive Survey on Integrating Differential Equations with Graph Neural Networks

83% match1 repo662025

Cite this paper

@article{poli2019graph,
  title  = {Graph Neural Ordinary Differential Equations},
  author = {Michael Poli and Stefano Massaroli and Junyoung Park and Atsushi Yamashita and Hajime Asama and Jinkyoo Park},
  year   = {2019},
  eprint = {1911.07532},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1911.07532}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1911.07532.svg)](https://codeofpaper.com/paper/1911.07532)

Discussion