Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction
Digital Discovery · 2025 · 4 (2) · 376-383
DOI: 10.1039/d4dd00199k ↗Kurz gefasst
Fachartikel in der Zeitschrift Digital Discovery, 2025. Verfasst von Youjia Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: National Science Foundation, National Institute of Standards and Technology, U.S. Department of Energy.
Abstract (Originalsprache)
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.
Förderung
- National Science Foundation
- National Institute of Standards and Technology
- U.S. Department of Energy
Zitieren
APA
Li, Y., Gupta, V., Kilic, M. N. T., Choudhary, K., Wines, D., Liao, W., Choudhary, A., & Agrawal, A. (2025). Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction. Digital Discovery, 4(2), 376-383. https://doi.org/10.1039/d4dd00199k
Vancouver
Li Y, Gupta V, Kilic MNT, Choudhary K, Wines D, Liao W, et al. Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction. Digital Discovery. 2025;4(2):376-383. doi:10.1039/d4dd00199k
BibTeX
@article{Li2025,
author = {Li, Youjia and Gupta, Vishu and Kilic, Muhammed Nur Talha and Choudhary, Kamal and Wines, Daniel and Liao, Wei-keng and Choudhary, Alok and Agrawal, Ankit},
title = {Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction},
journal = {Digital Discovery},
year = {2025},
volume = {4},
number = {2},
pages = {376--383},
doi = {10.1039/d4dd00199k}
}
EUVIMED