Advancing Extrapolative Predictions of Material Properties through Learning to Learn

TL;DR

This paper introduces a novel meta-learning approach using attention-based neural networks to improve the extrapolative prediction of material properties, enabling discovery of new materials beyond existing data.

Contribution

It develops a meta-learning framework with attention-based neural networks that enhances extrapolative generalization in material property prediction tasks.

Findings

Meta-learners achieve superior extrapolative generalization.

Models rapidly adapt to unseen material domains.

Effective in predicting properties of polymers and perovskites.

Abstract

Recent advancements in machine learning have showcased its potential to significantly accelerate the discovery of new materials. Central to this progress is the development of rapidly computable property predictors, enabling the identification of novel materials with desired properties from vast material spaces. However, the limited availability of data resources poses a significant challenge in data-driven materials research, particularly hindering the exploration of innovative materials beyond the boundaries of existing data. While machine learning predictors are inherently interpolative, establishing a general methodology to create an extrapolative predictor remains a fundamental challenge, limiting the search for innovative materials beyond existing data boundaries. In this study, we leverage an attention-based architecture of neural networks and meta-learning algorithms to acquire extrapolative generalization capability. The meta-learners, experienced repeatedly with arbitrarily generated extrapolative tasks, can acquire outstanding generalization capability in unexplored material spaces. Through the tasks of predicting the physical properties of polymeric materials and hybrid organic--inorganic perovskites, we highlight the potential of such extrapolatively trained models, particularly with their ability to rapidly adapt to unseen material domains in transfer learning scenarios.