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.
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