28 citations · 38 across the 2 of their papers we have counts for
2 papers
cs.LG2023★ 28 cited
Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs
Saro Passaro, C. Lawrence Zitnick
Graph neural networks that model 3D data, such as point clouds or atoms, are typically desired to be equivariant, i.e., equivariant to 3D rotations. Unfortunately equivaria…
cs.LG2020★ 10 cited
Directional Graph Networks
Dominique Beaini, Saro Passaro, Vincent Létourneau +3
The lack of anisotropic kernels in graph neural networks (GNNs) strongly limits their expressiveness, contributing to well-known issues such as over-smoothing. To overcome this lim…