LieTransformer: Equivariant self-attention for Lie Groups
Paper
•
2012.10885
•
Published
•
1
Euclidean signal on manifold domain for all inputs / outputs, with domain group action.
Note the data processed by this architecture does not have to belong to a Lie group; only to be acted upon by a Lie group. A lifting layer is introduced to convert the raw data into Lie group elements, which are then handled by the Lie Transformer. The attention layer is then equivariant.