Saved in:
Bibliographic Details
Main Authors: Laird, Lucas, Hsu, Circe, Bapat, Asilata, Walters, Robin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09571
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929678525136896
author Laird, Lucas
Hsu, Circe
Bapat, Asilata
Walters, Robin
author_facet Laird, Lucas
Hsu, Circe
Bapat, Asilata
Walters, Robin
contents Group theory has been used in machine learning to provide a theoretically grounded approach for incorporating known symmetry transformations in tasks from robotics to protein modeling. In these applications, equivariant neural networks use known symmetry groups with predefined representations to learn over geometric input data. We propose MatrixNet, a neural network architecture that learns matrix representations of group element inputs instead of using predefined representations. MatrixNet achieves higher sample efficiency and generalization over several standard baselines in prediction tasks over the several finite groups and the Artin braid group. We also show that MatrixNet respects group relations allowing generalization to group elements of greater word length than in the training set.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09571
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MatrixNet: Learning over symmetry groups using learned group representations
Laird, Lucas
Hsu, Circe
Bapat, Asilata
Walters, Robin
Machine Learning
Artificial Intelligence
Representation Theory
Group theory has been used in machine learning to provide a theoretically grounded approach for incorporating known symmetry transformations in tasks from robotics to protein modeling. In these applications, equivariant neural networks use known symmetry groups with predefined representations to learn over geometric input data. We propose MatrixNet, a neural network architecture that learns matrix representations of group element inputs instead of using predefined representations. MatrixNet achieves higher sample efficiency and generalization over several standard baselines in prediction tasks over the several finite groups and the Artin braid group. We also show that MatrixNet respects group relations allowing generalization to group elements of greater word length than in the training set.
title MatrixNet: Learning over symmetry groups using learned group representations
topic Machine Learning
Artificial Intelligence
Representation Theory
url https://arxiv.org/abs/2501.09571