Skip to yearly menu bar Skip to main content


Poster
in
Workshop: NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences

Enhancing the local expressivity of geometric graph neural networks

Sam Walton Norwood · Lars L Schaaf · Ilyes Batatia · Arghya Bhowmik · Gabor Csanyi


Abstract:

A central operation in geometric graph neural networks (GNNs) is the equivariant pairwise embedding, which encodes the local environment of each node as a learned representation. In this work, we examine the role of the pairwise embedding and consider a series of generalizations of its functional form beyond previous work. The new embeddings that we design considerably advance the state of the art in challenging distributions: as a highlight, when applied as an interatomic potential, we achieve a 29% relative reduction of force errors on diverse allotropes of lithium-intercalated carbon with a 4-fold reduction in parameter count. Furthermore, we demonstrate improved transferrability in molecular datasets by varying the locality of the network according to the depth of the representation.

Chat is not available.