Neural Variable-Order Fractional Differential Equation Networks
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (15) · 16109-16117
DOI: 10.1609/aaai.v39i15.33769 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Wenjun Cui und 6 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
The use of neural differential equation models in machine learning applications has gained significant traction in recent years. In particular, fractional differential equations (FDEs) have emerged as a powerful tool for capturing complex dynamics in various domains. While existing models have primarily focused on constant-order fractional derivatives, variable-order fractional operators offer a more flexible and expressive framework for modeling complex memory patterns. In this work, we introduce the Neural Variable-Order Fractional Differential Equation network (NvoFDE), a novel neural network framework that integrates variable-order fractional derivatives with learnable neural networks. Our framework allows for the modeling of adaptive derivative orders dependent on hidden features, capturing more complex feature-updating dynamics and providing enhanced flexibility. We conduct extensive experiments across multiple graph datasets to validate the effectiveness of our approach. Our results demonstrate that NvoFDE outperforms traditional constant-order fractional and integer models across a range of tasks, showcasing its superior adaptability and performance.
Zitieren
APA
Cui, W., Kang, Q., Li, X., Zhao, K., Tay, W. P., Deng, W., & Li, Y. (2025). Neural Variable-Order Fractional Differential Equation Networks. Proceedings of the AAAI Conference on Artificial Intelligence, 39(15), 16109-16117. https://doi.org/10.1609/aaai.v39i15.33769
Vancouver
Cui W, Kang Q, Li X, Zhao K, Tay WP, Deng W, et al. Neural Variable-Order Fractional Differential Equation Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(15):16109-16117. doi:10.1609/aaai.v39i15.33769
BibTeX
@article{Cui2025,
author = {Cui, Wenjun and Kang, Qiyu and Li, Xuhao and Zhao, Kai and Tay, Wee Peng and Deng, Weihua and Li, Yidong},
title = {Neural Variable-Order Fractional Differential Equation Networks},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {15},
pages = {16109--16117},
doi = {10.1609/aaai.v39i15.33769}
}
EUVIMED