Repository logo
 

MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Batatia, I 
Kovács, DP 
Simm, GNC 
Ortner, C 
Csányi, G 

Abstract

Creating fast and accurate force fields is a long-standing challenge in computational chemistry and materials science. Recently, several equivariant message passing neural networks (MPNNs) have been shown to outperform models built using other approaches in terms of accuracy. However, most MPNNs suffer from high computational cost and poor scalability. We propose that these limitations arise because MPNNs only pass two-body messages leading to a direct relationship between the number of layers and the expressivity of the network. In this work, we introduce MACE, a new equivariant MPNN model that uses higher body order messages. In particular, we show that using four-body messages reduces the required number of message passing iterations to just two, resulting in a fast and highly parallelizable model, reaching or exceeding state-of-the-art accuracy on the rMD17, 3BPA, and AcAc benchmark tasks. We also demonstrate that using higher order messages leads to an improved steepness of the learning curves.

Description

Keywords

Journal Title

Advances in Neural Information Processing Systems

Conference Name

NeurIPS 2021 · Thirty-fifth Annual Conference on Neural Information Processing Systems

Journal ISSN

1049-5258

Volume Title

35

Publisher

Publisher DOI

Sponsorship
Engineering and Physical Sciences Research Council (EP/X035891/1)
Engineering and Physical Sciences Research Council (EP/P022596/1)