Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteur principal: Maruyama, Yoshihiro
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914216564228096
author Maruyama, Yoshihiro
author_facet Maruyama, Yoshihiro
contents We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a topological category with Radon measures. Formulating linear and nonlinear layers in the categorical setup, we prove the equivariant universal approximation theorem in the general setting: the class of finite-depth CENNs is dense in the space of continuous equivariant transformations. We instantiate the framework for groups/groupoids, posets/lattices, graphs and cellular sheaves, deriving universal approximation theorems for them in a systematic manner. Categorical equivariant deep learning thus allows us to expand the horizons of equivariant deep learning beyond group actions, encompassing not only geometric symmetries but also contextual and compositional symmetries.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18417
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems
Maruyama, Yoshihiro
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
We develop a theory of category-equivariant neural networks (CENNs) that unifies group/groupoid-equivariant networks, poset/lattice-equivariant networks, graph and sheaf neural networks. Equivariance is formulated as naturality in a topological category with Radon measures. Formulating linear and nonlinear layers in the categorical setup, we prove the equivariant universal approximation theorem in the general setting: the class of finite-depth CENNs is dense in the space of continuous equivariant transformations. We instantiate the framework for groups/groupoids, posets/lattices, graphs and cellular sheaves, deriving universal approximation theorems for them in a systematic manner. Categorical equivariant deep learning thus allows us to expand the horizons of equivariant deep learning beyond group actions, encompassing not only geometric symmetries but also contextual and compositional symmetries.
title Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2511.18417