Self-supervised learning for crystal property prediction via denoising
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929479571472384 |
|---|---|
| author | New, Alexander Le, Nam Q. Pekala, Michael J. Stiles, Christopher D. |
| author_facet | New, Alexander Le, Nam Q. Pekala, Michael J. Stiles, Christopher D. |
| contents | Accurate prediction of the properties of crystalline materials is crucial for targeted discovery, and this prediction is increasingly done with data-driven models. However, for many properties of interest, the number of materials for which a specific property has been determined is much smaller than the number of known materials. To overcome this disparity, we propose a novel self-supervised learning (SSL) strategy for material property prediction. Our approach, crystal denoising self-supervised learning (CDSSL), pretrains predictive models (e.g., graph networks) with a pretext task based on recovering valid material structures when given perturbed versions of these structures. We demonstrate that CDSSL models out-perform models trained without SSL, across material types, properties, and dataset sizes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_17255 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised learning for crystal property prediction via denoising New, Alexander Le, Nam Q. Pekala, Michael J. Stiles, Christopher D. Machine Learning Materials Science Accurate prediction of the properties of crystalline materials is crucial for targeted discovery, and this prediction is increasingly done with data-driven models. However, for many properties of interest, the number of materials for which a specific property has been determined is much smaller than the number of known materials. To overcome this disparity, we propose a novel self-supervised learning (SSL) strategy for material property prediction. Our approach, crystal denoising self-supervised learning (CDSSL), pretrains predictive models (e.g., graph networks) with a pretext task based on recovering valid material structures when given perturbed versions of these structures. We demonstrate that CDSSL models out-perform models trained without SSL, across material types, properties, and dataset sizes. |
| title | Self-supervised learning for crystal property prediction via denoising |
| topic | Machine Learning Materials Science |
| url | https://arxiv.org/abs/2408.17255 |