Theoretical Aspects of Group Equivariant Neural Networks

04/10/2020
by   Carlos Esteves, et al.
0

Group equivariant neural networks have been explored in the past few years and are interesting from theoretical and practical standpoints. They leverage concepts from group representation theory, non-commutative harmonic analysis and differential geometry that do not often appear in machine learning. In practice, they have been shown to reduce sample and model complexity, notably in challenging tasks where input transformations such as arbitrary rotations are present. We begin this work with an exposition of group representation theory and the machinery necessary to define and evaluate integrals and convolutions on groups. Then, we show applications to recent SO(3) and SE(3) equivariant networks, namely the Spherical CNNs, Clebsch-Gordan Networks, and 3D Steerable CNNs. We proceed to discuss two recent theoretical results. The first, by Kondor and Trivedi (ICML'18), shows that a neural network is group equivariant if and only if it has a convolutional structure. The second, by Cohen et al. (NeurIPS'19), generalizes the first to a larger class of networks, with feature maps as fields on homogeneous spaces.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2021

Geometric Deep Learning and Equivariant Neural Networks

We survey the mathematical foundations of geometric deep learning, focus...
research
03/28/2018

Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)

Group equivariant and steerable convolutional neural networks (regular a...
research
06/24/2018

Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network

Recent work by Cohen et al. has achieved state-of-the-art results for le...
research
02/11/2018

On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups

Convolutional neural networks have been extremely successful in the imag...
research
03/30/2020

Stochastic Flows and Geometric Optimization on the Orthogonal Group

We present a new class of stochastic, geometrically-driven optimization ...
research
07/18/2022

e3nn: Euclidean Neural Networks

We present e3nn, a generalized framework for creating E(3) equivariant t...
research
06/13/2019

Neural Networks on Groups

Recent work on neural networks has shown that allowing them to build int...

Please sign up or login with your details

Forgot password? Click here to reset