Accurate, interpretable predictions of materials properties within transformer language models.

ABSTRACT: Property prediction accuracy has long been a key parameter of machine learning in materials informatics. Accordingly, advanced models showing state-of-the-art performance turn into highly parameterized black boxes missing interpretability. Here, we present an elegant way to make their reasoning transparent. Human-readable text-based descriptions automatically generated within a suite of open-source tools are proposed as materials representation. Transformer language models pretrained on 2 million peer-reviewed articles take as input well-known terms such as chemical composition, crystal symmetry, and site geometry. Our approach outperforms crystal graph networks by classifying four out of five analyzed properties if one considers all available reference data. Moreover, fine-tuned text-base

SUBMITTER: Korolev V 

PROVIDER: S-EPMC10591138 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature