G-RepsNet: A Fast and General Construction of Equivariant Networks for Arbitrary Matrix Groups

arXiv:2402.15413v1 Announce Type: new
Abstract: Group equivariance is a strong inductive bias useful in a wide range of deep learning tasks. However, constructing efficient equivariant networks for general groups and domains is difficult. Recent work by Finzi et al. (2021) directly solves the equivariance constraint for arbitrary matrix groups to obtain equivariant MLPs (EMLPs). But this method does not scale well and scaling is crucial in deep learning. Here, we introduce Group Representation Networks (G-RepsNets), a lightweight equivariant network for …

abstract arxiv bias construction cs.lg deep learning domains general inductive matrix networks tasks type work