Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

1 code implementation • NeurIPS 2023 • Jinwoo Kim, Tien Dat Nguyen, Ayhan Suleymanzade, Hyeokjun An, Seunghoon Hong

In contrary to equivariant architectures, we use an arbitrary base model such as an MLP or a transformer and symmetrize it to be equivariant to the given group by employing a small equivariant network that parameterizes the probabilistic distribution underlying the symmetrization.

Graph Classification Graph Regression +1