Equivariant Mesh Attention Networks

Understand

Equivariance to symmetries has proven to be a powerful inductive bias in deep learning research.

• Recent works on mesh processing have concentrated on various kinds of natural symmetries, including translations, rotations, scaling, node permutations, and gauge transformations.
• To date, no existing architecture is equivariant to all of these transformations.
• In this paper, we present an attention-based architecture for mesh data that is provably equivariant to all transformations mentioned above.