MatSKRAFT: A framework for large-scale materials knowledge extraction from scientific tables

2025-09-12

AI Summary

Extracting and leveraging semi-structured tabular knowledge from materials science literature remains challenging due to the lack of systematic, domain-aware methods. Method: This paper proposes a scientific-prior-guided graph neural network (GNN) approach that converts tables into heterogeneous graphs explicitly incorporating physical constraints—such as conservation laws and dimensional consistency—into the model architecture. Contribution/Results: The method achieves end-to-end parsing on 69,000 scientific tables, constructing a knowledge base of 535,000 records, including 104,000 material compositions absent from existing databases. It attains an 88.68% F1 score for property extraction and accelerates inference by 19–496× over state-of-the-art large language models. By bridging domain physics with graph representation learning, the approach significantly advances data-driven research into structure–property relationships in materials science.

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

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Scientific progress increasingly depends on synthesizing knowledge across vast literature, yet most experimental data remains trapped in semi-structured formats that resist systematic extraction and analysis. Here, we present MatSKRAFT, a computational framework that automatically extracts and integrates materials science knowledge from tabular data at unprecedented scale. Our approach transforms tables into graph-based representations processed by constraint-driven GNNs that encode scientific principles directly into model architecture. MatSKRAFT significantly outperforms state-of-the-art large language models, achieving F1 scores of 88.68 for property extraction and 71.35 for composition extraction, while processing data $19$-$496 imes$ faster than them (compared to the slowest and the fastest models, respectively) with modest hardware requirements. Applied to nearly 69,000 tables from more than 47,000 research publications, we construct a comprehensive database containing over 535,000 entries, including 104,000 compositions that expand coverage beyond major existing databases, pending manual validation. This systematic approach reveals previously overlooked materials with distinct property combinations and enables data-driven discovery of composition-property relationships forming the cornerstone of materials and scientific discovery.

Problem

• Extracting materials science knowledge from semi-structured tables
• Automating large-scale data integration from scientific literature
• Enabling systematic discovery of composition-property relationships

Innovation

• Graph-based table representations using constraint-driven GNNs
• Automated extraction from scientific tabular data
• Direct encoding of scientific principles into architecture