Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction
Youjia Li, Vishu Gupta, Muhammed Nur Talha Kilic, Kamal Choudhary, Daniel Wines, Wei‐keng Liao, Alok Choudhary, Ankit Agrawal
Abstract
This study combines Graph Neural Networks (GNNs) and Large Language Models (LLMs) to improve material property predictions. By leveraging both embeddings, this hybrid approach achieves up to a 25% improvement over GNN-only model in accuracy.
Topics & Concepts
Computer scienceProperty (philosophy)Artificial neural networkGraphArtificial intelligenceTheoretical computer scienceEpistemologyPhilosophyMachine Learning in Materials ScienceHydrogen embrittlement and corrosion behaviors in metalsComputational Drug Discovery Methods