Graph-text contrastive learning of inorganic crystal structure toward a foundation model of inorganic materials

Abstract

Developing foundation models for materials science has attracted attention. However, there is a lack of studies on inorganic materials due to the difficulty in the comprehensive representation of geometric concepts composing crystals: local atomic environments, their connections, and the global symmetries. We present a contrastive learning of inorganic crystal structure (CLICS) for embedding the geometric concepts, which contrasts texts representing the contextual patterns of geometries with the crystal graphs. We demonstrate that the geometric concepts are integrally embedded on the CLICS feature space, through experiments of concept prediction from crystal graphs, similar structure search, and few-shot/imbalanced crystal structure classification.

Keywords

• Machine learning
• inorganic materials
• crystal structure
• foundation model
• contrastive learning
• language model