Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data

by   Marc Finzi, et al.

The translation equivariance of convolutional layers enables convolutional neural networks to generalize well on image problems. While translation equivariance provides a powerful inductive bias for images, we often additionally desire equivariance to other transformations, such as rotations, especially for non-image data. We propose a general method to construct a convolutional layer that is equivariant to transformations from any specified Lie group with a surjective exponential map. Incorporating equivariance to a new group requires implementing only the group exponential and logarithm maps, enabling rapid prototyping. Showcasing the simplicity and generality of our method, we apply the same model architecture to images, ball-and-stick molecular data, and Hamiltonian dynamical systems. For Hamiltonian systems, the equivariance of our models is especially impactful, leading to exact conservation of linear and angular momentum.


page 5

page 20


LieTransformer: Equivariant self-attention for Lie Groups

Group equivariant neural networks are used as building blocks of group i...

Group Equivariant Conditional Neural Processes

We present the group equivariant conditional neural process (EquivCNP), ...

Lagrangian Neural Network with Differentiable Symmetries and Relational Inductive Bias

Realistic models of physical world rely on differentiable symmetries tha...

Continuous Methods : Hamiltonian Domain Translation

This paper proposes a novel approach to domain translation. Leveraging e...

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

Symmetries and equivariance are fundamental to the generalization of neu...

Automatic Symmetry Discovery with Lie Algebra Convolutional Network

Existing equivariant neural networks for continuous groups require discr...

Do ideas have shape? Plato's theory of forms as the continuous limit of artificial neural networks

We show that ResNets converge, in the infinite depth limit, to a general...

Code Repositories


SE(3)-equivariant point cloud networks for virtual screening

view repo


SE(3)-invariant neural networks for hotspot prediction

view repo


A simple implementation of the LieConv modules in PyTorch Geometric

view repo