Contrastive Learning of English Language and Crystal Graphs for Multimodal Representation of Materials Knowledge
This work addresses the problem of data scarcity and lack of semantic supervision for crystals in materials science, enabling more effective AI applications for materials design.
The paper tackles the challenge of integrating textual knowledge with crystal structures for AI-driven materials design by introducing a contrastive language-crystals model (CLaC) pre-trained on 126k synthetic crystal structure-text pairs, achieving state-of-the-art zero-shot generalization performance in understanding crystal structures.
Artificial intelligence (AI) is increasingly used for the inverse design of materials, such as crystals and molecules. Existing AI research on molecules has integrated chemical structures of molecules with textual knowledge to adapt to complex instructions. However, this approach has been unattainable for crystals due to data scarcity from the biased distribution of investigated crystals and the lack of semantic supervision in peer-reviewed literature. In this work, we introduce a contrastive language-crystals model (CLaC) pre-trained on a newly synthesized dataset of 126k crystal structure-text pairs. To demonstrate the advantage of using synthetic data to overcome data scarcity, we constructed a comparable dataset extracted from academic papers. We evaluate CLaC's generalization ability through various zero-shot cross-modal tasks and downstream applications. In experiments, CLaC achieves state-of-the-art zero-shot generalization performance in understanding crystal structures, surpassing latest large language models.