Weisfeiler Leman for Euclidean Equivariant Machine Learning

The $k$-Weifeiler-Leman ($k$-WL) graph isomorphism test hierarchy is a common method for assessing the expressive power of graph neural networks (GNNs). Recently, the $2$-WL test was proven to be complete on weighted graphs which encode $3\mathrm{D}$ point cloud data. Consequently, GNNs whose expressive power is equivalent to the $2$-WL test are provably universal on point clouds. Yet, this result is limited to invariant continuous functions on point clouds.
In this paper we extend this result in three ways: Firstly, we …

cloud cloud data cs.lg data encode gnns graph graph neural networks graphs machine machine learning networks neural networks power test