Self-supervised learning for crystal property prediction via denoising

Alexander New, Nam Q Le, Michael Pekala, Christopher D Stiles

Keywords: graph networks, self-supervised learning, material property prediction

TL;DR: We demonstrate the effectiveness of denoising-based self-supervised learning for material property prediction.

Abstract: 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.

Submission Number: 137