MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

• URL: http://arxiv.org/abs/2405.01029v2
• Date: Mon, 6 May 2024 11:35:57 GMT
• Title: MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts
• Authors: Jianan Zhou, Zhiguang Cao, Yaoxin Wu, Wen Song, Yining Ma, Jie Zhang, Chi Xu,
• Abstract summary: We propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE) We 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.
• Score: 26.790392171537754
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• Towards Efficient Pareto Set Approximation via Mixture of Experts Based Model Fusion [53.33473557562837]
  Solving multi-objective optimization problems for large deep neural networks is a challenging task due to the complexity of the loss landscape and the expensive computational cost. We propose a practical and scalable approach to solve this problem via mixture of experts (MoE) based model fusion. By ensembling the weights of specialized single-task models, the MoE module can effectively capture the trade-offs between multiple objectives.
  arXiv  Detail & Related papers  (2024-06-14T07:16:18Z)
• Cross-Problem Learning for Solving Vehicle Routing Problems [24.212686893913826]
  Existing neurals often train a deep architecture from scratch for each specific vehicle routing problem (VRP) This paper proposes the cross-problem learning to empirically assists training for different downstream VRP variants.
  arXiv  Detail & Related papers  (2024-04-17T18:17:50Z)
• Learning to Deliver: a Foundation Model for the Montreal Capacitated Vehicle Routing Problem [5.295700401553376]
  We present the Foundation Model for the Montreal Capacitated Vehicle Routing Problem (FM-MCVRP) FM-MCVRP is a novel Deep Learning (DL) model that approximates high-quality solutions to a variant of the Capacitated Vehicle Routing Problem (CVRP) We show that FM-MCVRP produces better MCVRP solutions than the training data and generalizes to larger sized problem instances not seen during training.
  arXiv  Detail & Related papers  (2024-02-28T16:02:29Z)
• Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization [18.298695520665348]
  Vehicle routing problems (VRPs) can be found in numerous real-world applications. In this work, we make the first attempt to tackle the crucial challenge of cross-problem generalization. Our proposed model can successfully solve VRPs with unseen attribute combinations in a zero-shot generalization manner.
  arXiv  Detail & Related papers  (2024-02-23T13:25:23Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Towards Omni-generalizable Neural Methods for Vehicle Routing Problems [14.210085924625705]
  This paper studies a challenging yet realistic setting, which considers generalization across both size and distribution in VRPs. We propose a generic meta-learning framework, which enables effective training of an model with the capability of fast adaptation to new tasks during inference.
  arXiv  Detail & Related papers  (2023-05-31T06:14:34Z)
• Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories [72.15369769265398]
  Machine learning has emerged as a promising paradigm for branching. We propose retro branching; a simple yet effective approach to RL for branching. We outperform the current state-of-the-art RL branching algorithm by 3-5x and come within 20% of the best IL method's performance on MILPs with 500 constraints and 1000 variables.
  arXiv  Detail & Related papers  (2022-05-28T06:08:07Z)
• Progressive Multi-stage Interactive Training in Mobile Network for Fine-grained Recognition [8.727216421226814]
  We propose a Progressive Multi-Stage Interactive training method with a Recursive Mosaic Generator (RMG-PMSI) First, we propose a Recursive Mosaic Generator (RMG) that generates images with different granularities in different phases. Then, the features of different stages pass through a Multi-Stage Interaction (MSI) module, which strengthens and complements the corresponding features of different stages. Experiments on three prestigious fine-grained benchmarks show that RMG-PMSI can significantly improve the performance with good robustness and transferability.
  arXiv  Detail & Related papers  (2021-12-08T10:50:03Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Model Fusion via Optimal Transport [64.13185244219353]
  We present a layer-wise model fusion algorithm for neural networks. We show that this can successfully yield "one-shot" knowledge transfer between neural networks trained on heterogeneous non-i.i.d. data.
  arXiv  Detail & Related papers  (2019-10-12T22:07:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.