Relaxed Equivariant Graph Neural Networks

Elyssa Hofgard, Rui Wang, Robin Walters, Tess Smidt

Track: Extended abstract

Keywords: Equivariant machine learning, symmetry breaking, relaxed convolution

TL;DR: We introduce a framework for relaxed E(3) graph equivariant neural networks that can learn and represent symmetry breaking within continuous groups.

Abstract: 3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems. We introduce a framework for relaxed $E(3)$ graph equivariant neural networks that can learn and represent symmetry breaking within continuous groups. Building on the existing e3nn framework, we propose the use of relaxed weights to allow for controlled symmetry breaking. We show empirically that these relaxed weights learn the correct amount of symmetry breaking.

Submission Number: 55