Examining graph neural networks for crystal structures: Limitations and opportunities for capturing periodicity
Name
sciadv.adi3245.pdf
Description
Published version
Size
2.02 MB
Format
Adobe PDF
Checksum (MD5)
513d6b3454f1a9d273007ebc7901e89a
Author(s)
Gong, Sheng
Yan, Keqiang
Xie, Tian
Shao-Horn, Yang
Gomez-Bombarelli, Rafael
Ji, Shuiwang
Grossman, Jeffrey C.
Date Issued
November 10, 2023
Journal
Science Advances
Publisher
American Association for the Advancement of Science
Citation
Sheng Gong et al. ,Examining graph neural networks for crystal structures: Limitations and opportunities for capturing periodicity.Sci. Adv.9, eadi3245 (2023).
Version
Final published version
Abstract
Graph neural networks (GNNs) have recently been used to learn the representations of crystal structures through an end-to-end data-driven approach. However, a systematic top-down approach to evaluate and understand the limitations of GNNs in accurately capturing crystal structures has yet to be established. In this study, we introduce an approach using human-designed descriptors as a compendium of human knowledge to investigate the extent to which GNNs can comprehend crystal structures. Our findings reveal that current state-of-the-art GNNs fall short in accurately capturing the periodicity of crystal structures. We analyze this failure by exploring three aspects: local expressive power, long-range information processing, and readout function. To address these identified limitations, we propose a straightforward and general solution: the hybridization of descriptors with GNNs, which directly supplements the missing information to GNNs. The hybridization enhances the predictive accuracy of GNNs for specific material properties, most notably phonon internal energy and heat capacity, which heavily rely on the periodicity of materials.
MIT Department
Massachusetts Institute of Technology. Department of Materials Science and Engineering
Massachusetts Institute of Technology. Department of Mechanical Engineering
Terms of Use
Creative Commons Attribution-Noncommercial
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1126/sciadv.adi3245
