In this paper, we evaluate an attention-based neural network architecture for the prediction of inorganic materials properties given access to nothing but each materials' chemical composition. We demonstrate that this novel application of self-attention for material property predictions strikingly outperforms both statistical and ensemble machine learning methods, as well as a fully-connected neural network.This Compositionally-Restricted Attention-Based network, referred to as CrabNet, is associated with improved test metrics across six of seven different tested materials properties from the AFLOW database. Moreover, we show that CrabNet outperforms other methods in the absence of chemical information, even when the statistical and ensemble learning techniques are given domain-specific chemical knowledge about the materials. Given its impressive improvement in predictive accuracy compared to previous methods, as well as its minimal hardware requirements for training and prediction, we feel confident that CrabNet, and the ideas explored within, will be central for future materials informatics research.
Update metadata, and added link to GitHub repository
CrabNet paper - SI