EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Determinism analysis in Hybrid-LLM-GNN modeling for materials property prediction

Youjia Li, Daniel Wines, Kamal Choudhary, Vishu Gupta, Muhammed Nur Talha Kilic, Sayak Chakrabarty, Wei-keng Liao, Alok Choudhary, Ankit Agrawal

Machine Learning: Science and Technology · 01.06.2026 · 7 (3) · 035031

DOI: 10.1088/2632-2153/ae696b ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 26.05.2026. Verfasst von Youjia Li und 8 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, U.S. Department of Commerce, National Institute of Standards and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Driven by advances in artificial intelligence and the growing availability of databases, machine learning (ML) now plays a central role in data-driven materials knowledge discovery. In studies that employ ML models, maintaining deterministic workflows is crucial for reproducibility, as it ensures that repeated runs with identical settings yield consistent and reliable predictions. Here, we conduct a determinism analysis of the recently proposed hybrid large language model-graph neural network (Hybrid-LLM-GNN) framework for material property prediction. Our study provides a comprehensive analysis of sources of non-determinism, with particular focus on variability introduced by hardware variations and software stacks across training and inference pipelines. By distinguishing different forms of determinism, we assess how discrepancies arise under varying execution conditions. In cases where results are non-deterministic, we further analyze and compare prediction differences to assess the impact of these variations. Our investigation uncovers systematic patterns in prediction discrepancies at the dataset level as well as variations at the individual sample level. Based on the findings, we identify the main sources of divergence and provide practical recommendations to improve deterministic behavior in ML-based materials property prediction workflows.

Förderung

  • National Science Foundation
  • U.S. Department of Commerce, National Institute of Standards and Technology

Zitieren

APA

Li, Y., Wines, D., Choudhary, K., Gupta, V., Kilic, M. N. T., Chakrabarty, S., Liao, W., Choudhary, A., & Agrawal, A. (2026). Determinism analysis in Hybrid-LLM-GNN modeling for materials property prediction. Machine Learning: Science and Technology, 7(3), 035031. https://doi.org/10.1088/2632-2153/ae696b

Vancouver

Li Y, Wines D, Choudhary K, Gupta V, Kilic MNT, Chakrabarty S, et al. Determinism analysis in Hybrid-LLM-GNN modeling for materials property prediction. Machine Learning: Science and Technology. 2026;7(3):035031. doi:10.1088/2632-2153/ae696b

BibTeX
@article{Li2026,
  author = {Li, Youjia and Wines, Daniel and Choudhary, Kamal and Gupta, Vishu and Kilic, Muhammed Nur Talha and Chakrabarty, Sayak and Liao, Wei-keng and Choudhary, Alok and Agrawal, Ankit},
  title = {Determinism analysis in Hybrid-LLM-GNN modeling for materials property prediction},
  journal = {Machine Learning: Science and Technology},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {035031},
  doi = {10.1088/2632-2153/ae696b}
}
Kostenlos starten →