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

By Ilyes Batatia, D. Kov'acs, Gregor N. C. Simm, Christoph Ortner, Gábor Csányi. 2022

1,193 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Materials Chemistry, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Materials Chemistry

In Molecular Biology

Citations in the corpus

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations (2023, neutral): “2 Related Works SE(3)/E(3) -Equivariant GNNs. Equivariant neural networks [5,7,11–18 , 31– 38] use equivariant irreps features built from vector spaces of irreducible representations ( irreps Invariant GNNs. Prior works [4,8,43–51] extract invariant information from 3D atomistic graphs and operate…”
A foundation model for atomistic materials chemistry. (2023, positive): “Here, we present MACE-MP-0, a new interatomic potential using the MACE architecture ( 35 ) that is trained just on the MPtrj dataset, and demonstrate its capabilities on an unprecedented range of qualitative and quantitative examples drawn from computational chemistry and materials science,…”
LitMOF: An LLM Multi-Agent for Literature-Validated Metal-Organic Frameworks Database Correction and Expansion (2025, unknown): “Specifically, the MACE-mh-1 model with OMAT PBE output head was employed[34, 41], augmented with a D3 dispersion correction using the Becke–Johnson damping scheme[42–44].”