Dissemin is shutting down on January 1st, 2025

Published in

Nature Research, npj Computational Materials, 1(7), 2021

DOI: 10.1038/s41524-021-00650-1

Links

Tools

Export citation

Search in Google Scholar

Atomistic Line Graph Neural Network for improved materials property predictions

Journal article published in 2021 by Kamal Choudhary ORCID, Brian DeCost ORCID
This paper is made freely available by the publisher.
This paper is made freely available by the publisher.

Full text: Download

Green circle
Preprint: archiving allowed
Red circle
Postprint: archiving forbidden
Green circle
Published version: archiving allowed
Data provided by SHERPA/RoMEO

Abstract

AbstractGraph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models. While most existing GNN models for atomistic predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which are critical for distinguishing many atomic structures. Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. We demonstrate that angle information can be explicitly and efficiently included, leading to improved performance on multiple atomistic prediction tasks. We ALIGNN models for predicting 52 solid-state and molecular properties available in the JARVIS-DFT, Materials project, and QM9 databases. ALIGNN can outperform some previously reported GNN models on atomistic prediction tasks with better or comparable model training speed.