Equivariant neural networks and equivarification
This work addresses the challenge of preserving symmetries in data for machine learning practitioners, but appears incremental as it builds on existing equivariant network concepts.
The paper tackles the problem of enforcing equivariance in neural networks by introducing a general method called equivarification, and shows that group convolutional neural networks are a special case of this framework.
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.