E (3)-Equivariant Mesh Neural Networks
Triangular meshes are widely used to represent three-dimensional objects. As a result,
many recent works have addressed the need for geometric deep learning on 3D meshes …
many recent works have addressed the need for geometric deep learning on 3D meshes …
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 …
method for assessing the expressive power of graph neural networks (GNNs). Recently, the …
On the Expressive Power of Sparse Geometric MPNNs
Motivated by applications in chemistry and other sciences, we study the expressive power of
message-passing neural networks for geometric graphs, whose node features correspond to …
message-passing neural networks for geometric graphs, whose node features correspond to …