Equivariant MLP
A JAX library for automatically generating equivariant neural network layers for arbitrary symmetry groups via constraint solving.
What is Equivariant MLP?
EMLP is a JAX library that programmatically generates equivariant layers for neural networks through constraint solving. It solves the problem of manually deriving symmetry-respecting layers by automatically computing bases for equivariant linear maps between arbitrary group representations, enabling the construction of models with built-in equivariance to transformations like rotations, permutations, or Lorentz boosts.
Researchers and practitioners in geometric deep learning, physics-informed machine learning, and anyone building models where incorporating symmetries (e.g., in particle physics, dynamical systems, or molecular modeling) is essential.
Developers choose EMLP because it automates the mathematically intensive process of deriving equivariant layers, supports a wide range of symmetry groups (including custom ones), and integrates with popular deep learning frameworks, significantly reducing development time for equivariant models.
Overview
A library for programmatically generating equivariant layers through constraint solving
Use Cases
Best For
- Building equivariant models for particle physics data with Lorentz symmetry
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
