Poster
in
Workshop: Geometry-grounded Representation Learning and Generative Modeling
Relaxed Equivariant Graph Neural Networks
Elyssa Hofgard · Rui Wang · Robin Walters · Tess Smidt
Keywords: [ Equivariant machine learning ] [ relaxed convolution ] [ symmetry breaking ]
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.
Chat is not available.