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

Daniel Levy, Sékou-Oumar Kaba, Carmelo Gonzales, Santiago Miret, Siamak Ravanbakhsh
9/6/2023
cs.LG

No confident code implementation found for this paper.

Abstract

We present a natural extension to E(n)-equivariant graph neural networks that uses multiple equivariant vectors per node. We formulate the extension and show that it improves performance across different physical systems benchmark tasks, with minimal differences in runtime or number of parameters. The proposed multichannel EGNN outperforms the standard singlechannel EGNN on N-body charged particle dynamics, molecular property predictions, and predicting the trajectories of solar system bodies. Given the additional benefits and minimal additional cost of multi-channel EGNN, we suggest that this extension may be of practical use to researchers working in machine learning for the physical sciences

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

85% match1 repo112024

E(n) Equivariant Graph Neural Networks

85% match1 repo5502021

Spatial Attention Kinetic Networks with E(n)-Equivariance

82% match1 repo92023

E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics

82% match2023

Lorentz Group Equivariant Neural Network for Particle Physics

82% match1 repo492020

E(n) Equivariant Topological Neural Networks

82% match1 repo412024

Cite this paper

@article{levy2023using,
  title  = {Using Multiple Vector Channels Improves E(n)-Equivariant Graph Neural Networks},
  author = {Daniel Levy and Sékou-Oumar Kaba and Carmelo Gonzales and Santiago Miret and Siamak Ravanbakhsh},
  year   = {2023},
  eprint = {2309.03139},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.03139v1}
}

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/2309.03139.svg)](https://codeofpaper.com/paper/2309.03139)

Discussion