2023
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
ICML 2023poster
Graph neural networks that model 3D data, such as point clouds or atoms, are typically desired to be $SO(3)$ equivariant, i.e., equivariant to 3D rotations. Unfortunately equivariant convolutions, which are a fundamental operation for equivariant networks, increase significantly in computational com…