EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Physics-Informed Variable-Order Fractional Graph Operator Learning on Irregular Domains

Guolong Zheng, Chen Hou, Tao Huang

Fractal and Fractional · 16.11.2026 · 10 (11) · 804

DOI: 10.3390/fractalfract10110804 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Fractal and Fractional, online erschienen am 16.11.2026. Verfasst von Guolong Zheng und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fujian Provincial Department of Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Variable-order fractional partial differential equations describe heterogeneous anomalous diffusion but can be costly to solve repeatedly at scale because of nonlocal memory and irregular geometry. We propose a physics-informed variable-order graph neural operator (PI-VO-GNO) in which the neural architecture is identical to a data-only graph operator and fractional calculus enters only through a differentiable variable-order Caputo residual. Across three paired seeds, the correct variable-order physics reduces prediction error by 10.44% in distribution and 5.17–6.90% under three distribution shifts, while reducing the true-order discrete residual by 37.7–46.8%. With only 10% of the training trajectories, prediction gains increase to 27.2–29.1%. Under 10% Gaussian corruption of the 25% training subset, PI-VO-GNO retains 13.2–18.6% lower prediction error. A model trained on 128-node graphs transfers to 192- and 256-node discretizations with 8.85–14.54% lower error. The physics loss adds no trainable parameters, only 7.7% training-step overhead, and negligible inference overhead. Reference-solver refinement exhibits monotonic spatial and temporal self-convergence. Mismatched integer- and fixed-order physics instead degrade prediction. Under a severe finite-element cross-discretization shift, field-error gains become nearly neutral, although physical-consistency gains persist. An interpolation control yields 2.70% mean trajectory discrepancy between inverse-distance and piecewise-linear (P1) transfer.

Förderung

  • National Natural Science Foundation of China
  • Fujian Provincial Department of Science and Technology

Zitieren

APA

Zheng, G., Hou, C., & Huang, T. (2026). Physics-Informed Variable-Order Fractional Graph Operator Learning on Irregular Domains. Fractal and Fractional, 10(11), 804. https://doi.org/10.3390/fractalfract10110804

Vancouver

Zheng G, Hou C, Huang T. Physics-Informed Variable-Order Fractional Graph Operator Learning on Irregular Domains. Fractal and Fractional. 2026;10(11):804. doi:10.3390/fractalfract10110804

BibTeX
@article{Zheng2026,
  author = {Zheng, Guolong and Hou, Chen and Huang, Tao},
  title = {Physics-Informed Variable-Order Fractional Graph Operator Learning on Irregular Domains},
  journal = {Fractal and Fractional},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {804},
  doi = {10.3390/fractalfract10110804}
}
Kostenlos starten →