Hybrid-LLM-GNN: integrating large language models and graph neural networks for enhanced materials property prediction
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.
Authors
- Youjia Li (ORCID: https://orcid.org/0000-0002-4755-679X)
- Ankit Agrawal (ORCID: https://orcid.org/0000-0002-5519-0302)
- Daniel Wines (ORCID: https://orcid.org/0000-0003-3855-3754)
- Kamal Choudhary (ORCID: https://orcid.org/0000-0001-9737-8074)
- Vishu Gupta (ORCID: https://orcid.org/0000-0002-4931-7194)
- Wei‐keng Liao (ORCID: https://orcid.org/0009-0008-9411-2543)
- Muhammed Nur Talha Kilic (ORCID: https://orcid.org/0000-0001-5879-8279)
- Alok N. Choudhary
Institutions
- Northwestern University (US)
- National Institute of Standards and Technology (US)
- Princeton University (US)
- Material Measurement Laboratory (US)
- Ludwig Cancer Research (US)
Publication Details
- Journal
- Digital Discovery
- Published
- 2024-12-18
- DOI
- https://doi.org/10.1039/d4dd00199k
- Citations
- 12
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 1.41
Funders
- National Science Foundation
- U.S. Department of Energy
- National Institute of Standards and Technology