Generalized Reduction to the Isotropy for Flexible Equivariant Neural Fields

2026-03-08

AI Summary

Existing equivariant neural fields struggle to handle inconsistent group actions on heterogeneous product spaces. This work proposes an isotropy subgroup reduction framework that establishes an orbit equivalence $(X \times M)/G \cong X/H$, thereby transforming the learning of $G$-invariant functions over the product space into learning $H$-invariant functions solely on $X$, where $H$ is the isotropy subgroup. By circumventing the stringent structural constraints on group actions imposed by prior methods, this approach significantly enhances modeling flexibility while preserving expressive capacity. It achieves, for the first time, a unified equivariant modeling framework applicable to arbitrary group actions and homogeneous configuration spaces.

Technology Category

• Machine Learning: Learning with Manifolds
• Computer Vision: Representation Learning for Vision
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Many geometric learning problems require invariants on heterogeneous product spaces, i.e., products of distinct spaces carrying different group actions, where standard techniques do not directly apply. We show that, when a group $G$ acts transitively on a space $M$, any $G$-invariant function on a product space $X \times M$ can be reduced to an invariant of the isotropy subgroup $H$ of $M$ acting on $X$ alone. Our approach establishes an explicit orbit equivalence $(X \times M)/G \cong X/H$, yielding a principled reduction that preserves expressivity. We apply this characterization to Equivariant Neural Fields, extending them to arbitrary group actions and homogeneous conditioning spaces, and thereby removing the major structural constraints imposed by existing methods.

Problem

• heterogeneous product spaces
• group actions
• invariants
• equivariant neural fields
• isotropy subgroup

Innovation

• equivariant neural fields
• isotropy subgroup
• orbit equivalence
• heterogeneous product spaces
• group actions