Skip to yearly menu bar Skip to main content


Poster

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

Marc Finzi · Samuel Stanton · Pavel Izmailov · Andrew Wilson

Keywords: [ Architectures ] [ Computer Vision ] [ Time Series and Sequence Models ] [ Other ] [ Deep Learning - General ]


Abstract:

The translation equivariance of convolutional layers enables CNNs 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.

Chat is not available.