MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
This work addresses the problem of limited generality in neural VRP solvers for researchers and practitioners, though it is incremental as it builds on existing mixture-of-experts and multi-task learning approaches.
The paper tackles the lack of a unified neural solver for vehicle routing problems (VRPs) by proposing MVMoE, a multi-task solver with mixture-of-experts, which significantly improves zero-shot generalization on 10 unseen VRP variants and shows decent results in few-shot and real-world settings.
Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes zero-shot generalization performance on 10 unseen VRP variants, and showcases decent results on the few-shot setting and real-world benchmark instances. We further conduct extensive studies on the effect of MoE configurations in solving VRPs, and observe the superiority of hierarchical gating when facing out-of-distribution data. The source code is available at: https://github.com/RoyalSkye/Routing-MVMoE.