Latent Space Symmetry Discovery

arXiv:2310.00105v2 Announce Type: replace
Abstract: Equivariant neural networks require explicit knowledge of the symmetry group. Automatic symmetry discovery methods aim to relax this constraint and learn invariance and equivariance from data. However, existing symmetry discovery methods are limited to simple linear symmetries and cannot handle the complexity of real-world data. We propose a novel generative model, Latent LieGAN (LaLiGAN), which can discover symmetries of nonlinear group actions. It learns a mapping from the data space to a latent space where …

abstract aim arxiv complexity cs.lg data discovery generative however knowledge learn linear networks neural networks novel simple space symmetry type world