Compositionally-Restricted Attention-Based Network for Materials Property Prediction

25 March 2021, Version 3
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

In this paper, we demonstrate a novel application of the Transformer self-attention mechanism. Our network, the Compositionally-Restricted Attention-Based network, referred to as 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.

For trained model weights, please see: http://doi.org/10.5281/zenodo.4633866

Keywords

machine learning
materials informatics
attention
self-attention
transformers
materials discovery
material screening
high-throughput screening
regression

Supplementary materials

Title
Description
Actions
Title
CrabNet - SI revision2
Description
Actions

Supplementary weblinks

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.