Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model

2024-04-03

Neural Information Processing Systems

AI Summary

Materials science knowledge is highly fragmented, and traditional experimental discovery is costly and time-consuming, impeding efficient novel material development; existing AI approaches suffer from poor data quality, heavy reliance on manual annotation, and insufficient semantic traceability. Method: This paper proposes an end-to-end knowledge graph (KG) construction paradigm tailored for multidisciplinary materials science, introducing a novel collaborative framework integrating large language models (LLMs) with domain-specific ontologies. It unifies named entity recognition, relation extraction, KG embedding, and link prediction to automatically extract structured triples from high-quality literature published over the past decade. Contribution/Results: The resulting Materials Knowledge Graph (MKG) comprises 162,605 nodes and 731,772 edges, enabling cross-disciplinary semantic alignment and traceable knowledge organization. Empirical evaluation demonstrates significant improvements in knowledge retrieval, logical reasoning, and property prediction—substantially reducing dependence on empirical trial-and-error.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Knowledge in materials science is widely dispersed across extensive scientific literature, posing significant challenges to the efficient discovery and integration of new materials. Traditional methods, often reliant on costly and time-consuming experimental approaches, further complicate rapid innovation. Addressing these challenges, the integration of artificial intelligence with materials science has opened avenues for accelerating the discovery process, though it also demands precise annotation, data extraction, and traceability of information. To tackle these issues, this article introduces the Materials Knowledge Graph (MKG), which utilizes advanced natural language processing techniques integrated with large language models to extract and systematically organize a decade's worth of high-quality research into structured triples, contains 162,605 nodes and 731,772 edges. MKG categorizes information into comprehensive labels such as Name, Formula, and Application, structured around a meticulously designed ontology, thus enhancing data usability and integration. By implementing network-based algorithms, MKG not only facilitates efficient link prediction but also significantly reduces reliance on traditional experimental methods. This structured approach not only streamlines materials research but also lays the groundwork for more sophisticated science knowledge graphs.

Problem

• Efficient discovery of dispersed materials science knowledge
• Reducing reliance on costly experimental methods
• Structuring unstructured data via knowledge graphs

Innovation

• Utilizes large language models for data extraction
• Constructs Materials Knowledge Graph with structured triples
• Implements network algorithms for link prediction