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

Join the Learning on Graphs and Geometry Reading Group: https://hannes-stark.com/logag-readin...

Paper “MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields": https://arxiv.org/abs/2206.07697

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 \emph{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.

Authors: Ilyes Batatia, Dávid Péter Kovács, Gregor N. C. Simm, Christoph Ortner, Gábor Csányi

Twitter Hannes:   / hannesstaerk  
Twitter Dominique:   / dom_beaini  
Twitter Valence Discovery:   / valence_ai  

Reading Group Slack: https://join.slack.com/t/logag/shared...

~

Chapters

00:00 - Intro
02:16 - Representations of clouds of particles in interaction
08:08 - The case of O93) for chemistry
21:51 - MACE: Message expansion
43:15 - Efficient machine learning on point clouds
52:57: MACE results
1:01:38 - Q+A and Discussion