EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling

Shun Wang iD, Shun-Li Shang iD, Zi-Kui Liu iD, Wenrui Hao iD

Proceedings of the National Academy of Sciences · 06.01.2026 · 123 (1)

DOI: 10.1073/pnas.2511227122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 02.01.2026. Verfasst von Shun Wang und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Penn State University, University Park, PA 16802. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NIGMS NIH HHS, U.S. Department of Energy (DOE), HHS | NIH | National Institute of General Medical Sciences (NIGMS).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Traditional entropy-based methods—such as cross-entropy loss in classification problems—have long been essential tools for representing the information uncertainty and physical disorder in data and for developing artificial intelligence algorithms. However, the rapid growth of data across various domains has introduced new challenges, particularly the integration of heterogeneous datasets with intrinsic disparities. To address this, we introduce a zentropy-enhanced neural network (ZENN), extending zentropy theory into the data science domain via intrinsic entropy, enabling more effective learning from heterogeneous data sources. ZENN simultaneously learns both energy and intrinsic entropy components, capturing the underlying structure of multisource data. To support this, we redesign the neural network architecture to better reflect the intrinsic properties and variability inherent in diverse datasets. We demonstrate the effectiveness of ZENN on classification tasks and energy landscape reconstructions, showing its superior generalization capabilities and robustness-particularly in predicting high-order derivatives. In image and text classification tasks, ZENN demonstrates superior generalization by introducing a learnable temperature variable that models latent multisource heterogeneity, allowing it to surpass state-of-the-art models on CIFAR-10/100, BBC News, and AG News. As a practical application in materials science, we employ ZENN to reconstruct the Helmholtz energy landscape of Fe 3 Pt using data generated from density functional theory and capture key material behaviors, including negative thermal expansion and the critical point in the temperature–pressure space. Overall, this work presents a zentropy-grounded framework for data-driven machine learning, positioning ZENN as a versatile and robust approach for scientific problems involving complex, heterogeneous datasets.

Schlagwörter

Stichwörter der Autor:innen

classificationcritical phenomenadata-driven modelingnegative thermal expansionzentropy-enhanced neural network

Autor:innen und Institutionen

  • Department of Mathematics, Penn State University, University Park, PA 16802.
  • Department of Materials Science and Engineering, Penn State University, University Park, PA 16802.

ORCID-Profile: Shun Wang, Shun-Li Shang, Zi-Kui Liu, Wenrui Hao

Förderung

  • NIGMS NIH HHS
  • U.S. Department of Energy (DOE)
  • HHS | NIH | National Institute of General Medical Sciences (NIGMS)

Zitieren

APA

Wang, S., Shang, S. L., Liu, Z. K., & Hao, W. (2026). ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling. Proceedings of the National Academy of Sciences, 123(1). https://doi.org/10.1073/pnas.2511227122

Vancouver

Wang S, Shang SL, Liu ZK, Hao W. ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling. Proceedings of the National Academy of Sciences. 2026;123(1). doi:10.1073/pnas.2511227122

BibTeX
@article{Wang2026,
  author = {Wang, Shun and Shang, Shun-Li and Liu, Zi-Kui and Hao, Wenrui},
  title = {ZENN: A thermodynamics-inspired computational framework for heterogeneous data–driven modeling},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2026},
  volume = {123},
  number = {1},
  doi = {10.1073/pnas.2511227122}
}
Kostenlos starten →