Work

Compositionally restricted attention-based network for materials property predictions

Year: 2021
Type: article
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 (), explores the area of structure-agnostic materials property predictions when only a chemical formula is provided. Our results show that ’s performance matches or exceeds current best-practice methods on nearly all of 28 total benchmark datasets. We also demonstrate how ’s architecture lends itself towards model interpretability by showing different visualization approaches that are made possible by its design. We feel confident that and its attention-based framework will be of keen interest to future materials informatics researchers.
Language: English
Open Access status: gold
Estimated APC paid: $2,890
OpenAlex ID: W3116783766
FWCI: 9.966
Cites: 79
Cited by: 355
Related to: 10