Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
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.
Code (2)
Tasks
Inductive BiasTranslationSimilar Papers 제목 키워드 기반
Learning Equivariant Representations
State-of-the-art deep learning systems often require large amounts of data and computation. For this reason, leveraging known or unknown structure of the data is paramount. Convolutional neural networks (CNNs) are succes…
3D Shape ClassificationGeneral Classificationimage-classificationImage Classification+3Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups
Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations…
Computational EfficiencyRotated MNISTB-Spline CNNs on Lie Groups
Group convolutional neural networks (G-CNNs) can be used to improve classical CNNs by equipping them with the geometric structure of groups. Central in the success of G-CNNs is the lifting of feature maps to higher dimen…
Face AlignmentHarmformer: Harmonic Networks Meet Transformers for Continuous Roto-Translation Equivariance
CNNs exhibit inherent equivariance to image translation, leading to efficient parameter and data usage, faster learning, and improved robustness. The concept of translation equivariant networks has been successfully exte…
TranslationSymmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks
There has been much recent interest in designing neural networks (NNs) with relaxed equivariance, which interpolate between exact equivariance and full flexibility for consistent performance gains. In a separate line of …