Moran, Michael, Gaultois, Michael W 
ORCID: 0000-0003-2172-2507, Gusev, Vladimir V ORCID: 0000-0002-2815-607X and Rosseinsky, Matthew J ORCID: 0000-0002-1910-2483
(2023)
Site-Net: using global self-attention and real-space supercells to capture long-range interactions in crystal structures
DIGITAL DISCOVERY, 2 (5).
pp. 1297-1310.
ISSN 2635-098X, 2635-098X
Abstract
Site-Net is a transformer architecture that models the periodic crystal structures of inorganic materials as a labelled point set of atoms and relies entirely on global self-attention and geometric information to guide learning. Site-Net processes standard crystallographic information files to generate a large real-space supercell, and the importance of interactions between all atomic sites is flexibly learned by the model for the prediction task presented. The attention mechanism is probed to reveal Site-Net can learn long-range interactions in crystal structures, and that specific attention heads become specialised to deal with primarily short- or long-range interactions. We perform a preliminary hyperparameter search and train Site-Net using a single graphics processing unit (GPU), and show Site-Net achieves state-of-the-art performance on a standard band gap regression task.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | 46 Information and Computing Sciences, 4611 Machine Learning |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 07 Aug 2024 14:00 |
| Last Modified: | 16 Jun 2026 20:14 |
| DOI: | 10.1039/d3dd00005b |
| Open Access URL: | https://doi.org/10.1039/D3DD00005B |
| Related Websites: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3183427 |
| Disclaimer: | The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate. |
Altmetric
Altmetric