Atomistic Line Graph Neural Network for Improved Materials Property Predictions

Published

December 5, 2021

Author(s)

Kamal Choudhary, Brian DeCost

Abstract

Graph 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 by up to 85% in accuracy with better or comparable model training speed.

Citation

npj Computational Materials

Pub Type

Journals

Download Paper

https://doi.org/10.1038/s41524-021-00650-1

Local Download

Keywords

Graph Neural Network, density functional theory, deep learning

Citation

Choudhary, K. and DeCost, B. (2021), Atomistic Line Graph Neural Network for Improved Materials Property Predictions, npj Computational Materials, [online], https://doi.org/10.1038/s41524-021-00650-1, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=932627 (Accessed October 9, 2025)