A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
Published in
International Conference on Machine Learning(2021)External Links:
TL
TL;DR
This work provides a completely general algorithm for solving for the equivariant layers of matrix groups, and constructs multilayer perceptrons equivariants to multiple groups that have never been tackled before.
Abstract
Symmetries and equivariance are fundamental to the generalization of neural networks on domains such as images, graphs, and point clouds. Existing work has primarily focused on a small number of groups, such as the translation, rotation, and permutation groups. In this work we provide a completely general algorithm for solving for the equivariant layers of matrix groups. In addition to recovering solutions from other works as special cases, we construct multilayer perceptrons equivariant to multiple groups that have never been tackled before, including $\mathrm{O}(1,3)$, $\mathrm{O}(5)$, $\mathrm{Sp}(n)$, and the Rubik's cube group. Our approach outperforms non-equivariant baselines, with applications to particle physics and dynamical systems. We release our software library to enable researchers to construct equivariant layers for arbitrary matrix groups.
References49 items
1
A Wigner-Eckart Theorem for Group Equivariant Convolution Kernels
2
Probabilistic Numeric Convolutional Neural Networks
3
On the Universality of Rotation Equivariant Point Cloud Networks
4
MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning
5