E(n) Equivariant Graph Neural Networks

Victor Garcia Satorras, Emiel Hoogeboom, Max Welling
2/19/2021
cs.LGstat.ML

Official code: vgsatorras/egnn (550 stars, MIT, last commit 2022-02-23).

Abstract

This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs). In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance. In addition, whereas existing methods are limited to equivariance on 3 dimensional spaces, our model is easily scaled to higher-dimensional spaces. We demonstrate the effectiveness of our method on dynamical systems modelling, representation learning in graph autoencoders and predicting molecular properties.

View on arXivView PDF

Code Implementations(1)

vgsatorras/egnnOfficial100%
MIT
55090Shell, PythonMay 11, 20214 years agoMIT

Similar Papers

Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning

86% match2025

E(n) Equivariant Topological Neural Networks

85% match1 repo412024

Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks

85% match2023

Equivariant Graph Neural Operator for Modeling 3D Dynamics

84% match2 repos652024

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

84% match1 repo852024

Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks

84% match1 repo112024

Cite this paper

@article{satorras2021en,
  title  = {E(n) Equivariant Graph Neural Networks},
  author = {Victor Garcia Satorras and Emiel Hoogeboom and Max Welling},
  year   = {2021},
  eprint = {2102.09844},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2102.09844}
}

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/2102.09844.svg)](https://codeofpaper.com/paper/2102.09844)

Discussion