Contrastive Learning of English Language and Crystal Graphs for Multimodal Representation of Materials Knowledge

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Park, Yang Jeong, Kumaran, Mayank, Hsu, Chia-Wei, Olivetti, Elsa, Li, Ju
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929726893850624
author Park, Yang Jeong
Kumaran, Mayank
Hsu, Chia-Wei
Olivetti, Elsa
Li, Ju
author_facet Park, Yang Jeong
Kumaran, Mayank
Hsu, Chia-Wei
Olivetti, Elsa
Li, Ju
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_16451
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contrastive Learning of English Language and Crystal Graphs for Multimodal Representation of Materials Knowledge
Park, Yang Jeong
Kumaran, Mayank
Hsu, Chia-Wei
Olivetti, Elsa
Li, Ju
Computation and Language
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.
title Contrastive Learning of English Language and Crystal Graphs for Multimodal Representation of Materials Knowledge
topic Computation and Language
url https://arxiv.org/abs/2502.16451