E(n) Equivariant Graph Neural Networks
Victor Garcia Satorras 1 Emiel Hoogeboom 1 Max Welling 1
Abstract
This paper introduces a new model to learn graph
neural networks equivariant to rotations, transla-
tions, reflections and permutations called E(n)-
Equivariant Graph Neural Networks (EGNNs). In
contrast with existing methods, our work does not
require computationally expensive higher-order
representations in intermediate layers while it
s ...


雷达卡




京公网安备 11010802022788号







