Enhancing the Cross-Size Generalization for Solving Vehicle Routing Problems via Continual Learning

• URL: http://arxiv.org/abs/2510.10262v2
• Date: Sun, 19 Oct 2025 23:48:02 GMT
• Title: Enhancing the Cross-Size Generalization for Solving Vehicle Routing Problems via Continual Learning
• Authors: Jingwen Li, Zhiguang Cao, Yaoxin Wu, Tang Liu,
• Abstract summary: Existing deep models for vehicle routing problems are typically trained and evaluated using instances of a single size.<n>This substantially limits their ability to generalize across different problem sizes.<n>We propose a continual learning based framework that sequentially trains a deep model with instances of ascending problem sizes.
• Score: 44.178497470932435
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Exploring machine learning techniques for addressing vehicle routing problems has attracted considerable research attention. To achieve decent and efficient solutions, existing deep models for vehicle routing problems are typically trained and evaluated using instances of a single size. This substantially limits their ability to generalize across different problem sizes and thus hampers their practical applicability. To address the issue, we propose a continual learning based framework that sequentially trains a deep model with instances of ascending problem sizes. Specifically, on the one hand, we design an inter-task regularization scheme to retain the knowledge acquired from smaller problem sizes in the model training on a larger size. On the other hand, we introduce an intra-task regularization scheme to consolidate the model by imitating the latest desirable behaviors during training on each size. Additionally, we exploit the experience replay to revisit instances of formerly trained sizes for mitigating the catastrophic forgetting. Experimental results show that our approach achieves predominantly superior performance across various problem sizes (either seen or unseen in the training), as compared to state-of-the-art deep models including the ones specialized for generalizability enhancement. Meanwhile, the ablation studies on the key designs manifest their synergistic effect in the proposed framework.

Related papers

• Architecture Decoupling Is Not All You Need For Unified Multimodal Model [64.19284951218098]
  We propose Attention Interaction Alignment (AIA) loss, which explicitly learns Task-Specific multimodal interaction patterns during training.<n>AIA not only refines cross-modal attention patterns, but also boosts both generation and understanding performance.
  arXiv  Detail & Related papers  (2025-11-27T17:55:25Z)
• HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness [49.72591739116668]
  Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs)<n>However, prevalent methods like GRPO often fail when task difficulty exceeds the model's capacity, leading to reward sparsity and inefficient training.<n>We propose HINT: Helping Ineffective rollouts Navigate Towards effectiveness, an adaptive hinting framework.
  arXiv  Detail & Related papers  (2025-10-10T13:42:03Z)
• Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning [3.0711362702464684]
  We introduce a novel learning framework driven by Large Language Models (LLMs)<n>Unlike prevailing techniques that necessitate joint training with the neural network, our approach operates exclusively during the inference phase.<n>Our method enables a backbone model (trained on 100-node instances) to achieve superior performance on large-scale Traveling Salesman Problem (TSP) and Capacitated Vehicle Routing Problem (CVRP) of up to 100K nodes from diverse distributions.
  arXiv  Detail & Related papers  (2025-06-03T03:15:22Z)
• Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion [86.6191592951269]
  Merging models fine-tuned from common extensively pretrained large model but specialized for different tasks has been demonstrated as a cheap and scalable strategy to construct a multitask model that performs well across diverse tasks. We propose the CONtinuous relaxation dis (Concrete) subspace learning method to identify a common lowdimensional subspace and utilize its shared information track interference problem without sacrificing performance.
  arXiv  Detail & Related papers  (2023-12-11T07:24:54Z)
• Too Big, so Fail? -- Enabling Neural Construction Methods to Solve Large-Scale Routing Problems [10.832715681422842]
  We show that even state-of-the-art neural construction methods are outperformed by simple iterations. We propose to use the ruin recreate principle that alternates between completely destroying a localized part of the solution and then recreating an improved variant.
  arXiv  Detail & Related papers  (2023-09-29T09:36:37Z)
• 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)
• Prototype-guided Cross-task Knowledge Distillation for Large-scale Models [103.04711721343278]
  Cross-task knowledge distillation helps to train a small student model to obtain a competitive performance. We propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios.
  arXiv  Detail & Related papers  (2022-12-26T15:00:42Z)
• DL-DRL: A double-level deep reinforcement learning approach for large-scale task scheduling of multi-UAV [65.07776277630228]
  We propose a double-level deep reinforcement learning (DL-DRL) approach based on a divide and conquer framework (DCF) Particularly, we design an encoder-decoder structured policy network in our upper-level DRL model to allocate the tasks to different UAVs. We also exploit another attention based policy network in our lower-level DRL model to construct the route for each UAV, with the objective to maximize the number of executed tasks.
  arXiv  Detail & Related papers  (2022-08-04T04:35:53Z)
• Attention, Filling in The Gaps for Generalization in Routing Problems [5.210197476419621]
  This paper aims at encouraging the consolidation of the field through understanding and improving current existing models. We first target model discrepancies by adapting the Kool et al. method and its loss function for Sparse Dynamic Attention. We then target inherent differences through the use of a mixed instance training method that has been shown to outperform single instance training in certain scenarios.
  arXiv  Detail & Related papers  (2022-07-14T21:36:51Z)
• Supervised Permutation Invariant Networks for Solving the CVRP with Bounded Fleet Size [3.5235974685889397]
  Learning to solve optimization problems, such as the vehicle routing problem, offers great computational advantages. We propose a powerful supervised deep learning framework that constructs a complete tour plan from scratch while respecting an apriori fixed number of vehicles. In combination with an efficient post-processing scheme, our supervised approach is not only much faster and easier to train but also competitive results.
  arXiv  Detail & Related papers  (2022-01-05T10:32:18Z)
• Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning [90.93035276307239]
  We propose an information theoretic regularization objective and an annealing-based optimization method to achieve better generalization ability in RL agents. We demonstrate the extreme generalization benefits of our approach in different domains ranging from maze navigation to robotic tasks. This work provides a principled way to improve generalization in RL by gradually removing information that is redundant for task-solving.
  arXiv  Detail & Related papers  (2020-08-03T02:24:20Z)

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.