Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems
IEEE Transactions on Intelligent Transportation Systems · 2026-08 · 27 (8) · 9690-9699
DOI: 10.1109/tits.2026.3679738 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-08. Verfasst von Shaodi Feng und 7 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Sichuan Province, China.
Abstract (Originalsprache)
Deep learning has been increasingly adopted in intelligent transportation systems (ITS) to address vehicle routing problems (VRPs) that arise in real-world operations such as fleet management, urban logistics, and dynamic dispatching. However, most neural solvers are trained to tackle VRP instances in a relatively monotonous context, e.g., simplifying VRPs by using Euclidean distance between nodes and adhering to a single problem size, which harms their off-the-shelf application in different scenarios. To enhance their versatility, this paper presents a novel lifelong learning framework that incrementally trains a neural solver to manage VRPs in distinct contexts. Specifically, we propose a lifelong learner (LL), exploiting a Transformer network as the backbone, to solve a series of VRPs. The inter-context self-attention mechanism is proposed within LL to transfer the knowledge obtained from solving preceding VRPs into the succeeding ones. On top of that, we develop a dynamic context scheduler (DCS), employing the cross-context experience replay to further facilitate LL looking back on the attained policies of solving preceding VRPs. Extensive results on synthetic and benchmark instances (problem sizes up to 18k) show that our LL is capable of discovering effective policies for tackling generic VRPs in varying contexts. The source code is available: https://github.com/fsdfsd123/Lifelong-Learner-Discovering-More-Versatile-Neural-Solvers-for-Routing-Problems.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Sichuan Province, China
Zitieren
APA
Feng, S., Lin, Z., Zhou, J., Zhang, C., Li, J., Chen, K., Jayavelu, S., & Ong, Y. (2026). Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems. IEEE Transactions on Intelligent Transportation Systems, 27(8), 9690-9699. https://doi.org/10.1109/tits.2026.3679738
Vancouver
Feng S, Lin Z, Zhou J, Zhang C, Li J, Chen K, et al. Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems. IEEE Transactions on Intelligent Transportation Systems. 2026;27(8):9690-9699. doi:10.1109/tits.2026.3679738
BibTeX
@article{Feng2026,
author = {Feng, Shaodi and Lin, Zhuoyi and Zhou, Jianan and Zhang, Cong and Li, Jingwen and Chen, Kuan-Wen and Jayavelu, Senthilnath and Ong, Yew-Soon},
title = {Lifelong Learner: Discovering Versatile Neural Solvers for Vehicle Routing Problems},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {8},
pages = {9690--9699},
doi = {10.1109/tits.2026.3679738}
}
EUVIMED