MRS Meetings and Events


DS01.01.01 2022 MRS Spring Meeting

Graph Neural Network for Improved Property Predictions of Molecules, Solids and Metal Organic Framworks

When and Where

May 8, 2022
9:00am - 9:15am

Hawai'i Convention Center, Level 3, Lili'U Theater, 310



Kamal Choudhary1

National Institute of Standards and Technology1


Kamal Choudhary1

National Institute of Standards and Technology1
Graph neural networks (GNN) have been shown to provide substantial performance improvements for representing and modeling atomistic materials 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 use ALIGNN models for predicting 60 solid-state and molecular properties available in the JARVIS-DFT, Materials project, h-MOF 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.

Symposium Organizers

Mathieu Bauchy, University of California, Los Angeles
Mathew Cherukara, Argonne National Laboratory
Grace Gu, University of California, Berkeley
Badri Narayanan, University of Louisville

Publishing Alliance

MRS publishes with Springer Nature