English

Equivariant neural networks and equivarification

Machine Learning 2025-11-19 v5 Computer Vision and Pattern Recognition Machine Learning

Abstract

Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Keywords

Cite

@article{arxiv.1906.07172,
  title  = {Equivariant neural networks and equivarification},
  author = {Erkao Bao and Jingcheng Lu and Linqi Song and Nathan Hart-Hodgson and William Parson and Yanheng Zhou},
  journal= {arXiv preprint arXiv:1906.07172},
  year   = {2025}
}

Comments

More explanations and experiments were added; a theoretical comparison with G-CNN was added

R2 v1 2026-06-23T09:55:59.981Z