ICLR2024
Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
Shih-Hsin Wang, Yung-Chang Hsu, Justin M. Baker, Andrea L. Bertozzi, Jack Xin, Bao Wang
6 citations
Abstract
x i represents the input coordinates of node i, * UPD and AGG are learnable update and aggregate equivariant functions, re-spectively, where • denotes a multiset, * N (k) i