Refining Graph Learning Dynamics with the Riemann–Liouville Fractional Derivative
Journal of Intelligent Computing and Networking · 01.06.2026 · 2 (2) · 14-29
DOI: 10.64509/jicn.22.93 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligent Computing and Networking, online erschienen am 01.06.2026. Verfasst von Yufeng Peng und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
We introduce the Riemann–Liouville Graph neural Fractional-order Differential Equation (RL-GFDE), a novel continuous Graph Neural Network (GNN) framework that incorporates the Riemann–Liouville (RL) fractional derivative. This framework effectively captures feature updating dynamics with pronounced memory effects, offering an advantage over standard graph neural ordinary differential equation (ODE) models that rely solely on integer-order derivatives. Our contributions are twofold: First, we establish a generalized continuous GNN framework grounded in fractional calculus. We also provide a comprehensive convergence analysis for the solvers applied to RL-GFDE, ensuring precision and efficiency in our method. Second, through theoretical analysis and extensive empirical experiments, we demonstrate the enhanced performance of RL-GFDE by comparing fractional adaptations of various well-known contemporary graph neural ODE models against their original integer-order counterparts. Our results validate the efficacy of RL-GFDE, showcasing its versatility as an extension to boost the performance of graph neural ODE models in various applications.
Zitieren
APA
Peng, Y., Qiyu, K., Zhao, K., Li, X., & Ding, Q. (2026). Refining Graph Learning Dynamics with the Riemann–Liouville Fractional Derivative. Journal of Intelligent Computing and Networking, 2(2), 14-29. https://doi.org/10.64509/jicn.22.93
Vancouver
Peng Y, Qiyu K, Zhao K, Li X, Ding Q. Refining Graph Learning Dynamics with the Riemann–Liouville Fractional Derivative. Journal of Intelligent Computing and Networking. 2026;2(2):14-29. doi:10.64509/jicn.22.93
BibTeX
@article{Peng2026,
author = {Peng, Yufeng and Qiyu, Kang and Zhao, Kai and Li, Xuhao and Ding, Qinxu},
title = {Refining Graph Learning Dynamics with the Riemann–Liouville Fractional Derivative},
journal = {Journal of Intelligent Computing and Networking},
year = {2026},
volume = {2},
number = {2},
pages = {14--29},
doi = {10.64509/jicn.22.93}
}
EUVIMED