Automatic Symmetry Discovery with Lie Algebra Convolutional Network

Abstract

Existing equivariant neural networks require prior knowledge of the symmetry group and discretization for continuous groups. We propose to work with Lie algebras (infinitesimal generators) instead of Lie groups. Our model, the Lie algebra convolutional network (L-conv) can automatically discover symmetries and does not require discretization of the group. We show that L-conv can serve as a building block to construct any group equivariant feedforward architecture. Both CNNs and Graph Convolutional Networks can be expressed as L-conv with appropriate groups. We discover direct connections between L-conv and physics: (1) group invariant loss generalizes field theory (2) Euler-Lagrange equation measures the robustness, and (3) equivariance leads to conservation laws and Noether current.These connections open up new avenues for designing more general equivariant networks and applying them to important problems in physical sciences

References in corpus (16)

• Semi-Supervised Classification with Graph Convolutional Networks
• Neural Message Passing for Quantum Chemistry
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Group Equivariant Convolutional Networks
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• Equivariance Through Parameter-Sharing
• General $E(2)$-Equivariant Steerable CNNs
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• On Learning Sets of Symmetric Elements
• Learning the Irreducible Representations of Commutative Lie Groups
• Learning Invariances in Neural Networks
• A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
• Meta-Learning Symmetries by Reparameterization
• An Unsupervised Algorithm For Learning Lie Group Transformations
• Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics
• Universal Equivariant Multilayer Perceptrons

Cited by in corpus (4)

• Hamiltonian Neural Networks with Automatic Symmetry Detection
• Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery
• Learning dissection trajectories from expert surgical videos via imitation learning with equivariant diffusion
• SymmetryLens: Unsupervised Symmetry Learning via Locality and Density Preservation