We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Compositionally restricted attention-based network for materials property predictions.
- Authors
Wang, Anthony Yu-Tung; Kauwe, Steven K.; Murdock, Ryan J.; Sparks, Taylor D.
- Abstract
In this paper, we demonstrate an application of the Transformer self-attention mechanism in the context of materials science. Our network, the Compositionally Restricted Attention-Based network (CrabNet), explores the area of structure-agnostic materials property predictions when only a chemical formula is provided. Our results show that CrabNet's performance matches or exceeds current best-practice methods on nearly all of 28 total benchmark datasets. We also demonstrate how CrabNet's architecture lends itself towards model interpretability by showing different visualization approaches that are made possible by its design. We feel confident that CrabNet and its attention-based framework will be of keen interest to future materials informatics researchers.
- Publication
NPJ Computational Materials, 2021, Vol 7, Issue 1, p1
- ISSN
2057-3960
- Publication type
Article
- DOI
10.1038/s41524-021-00545-1