Saved in:
Bibliographic Details
Main Authors: Jiao, Dongbin, Chen, Zisheng, Wang, Xianyi, Shi, Jintao, Liu, Shengcai, Yan, Shi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.00488
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910009557778432
author Jiao, Dongbin
Chen, Zisheng
Wang, Xianyi
Shi, Jintao
Liu, Shengcai
Yan, Shi
author_facet Jiao, Dongbin
Chen, Zisheng
Wang, Xianyi
Shi, Jintao
Liu, Shengcai
Yan, Shi
contents Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of heuristics and the limited generalization of neural solvers on massive graphs. We propose OD-DEAL, an adversarial learning framework that tightly integrates hybrid genetic search (HGS) and online barycenter clustering (BCC) decomposition, and leverages high-fidelity knowledge distillation to transfer expert heuristic behavior. OD-DEAL trains a graph attention network (GAT)-based generative policy through a minimax game, in which divide-and-conquer strategies from a hybrid expert are distilled into dense surrogate rewards. This enables high-quality, clustering-free inference on large-scale instances. Empirical results demonstrate that OD-DEAL achieves state-of-the-art (SOTA) real-time CVRP performance, solving 10000-node instances with near-constant neural scaling. This uniquely enables the sub-second, heuristic-quality inference required for dynamic large-scale deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00488
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle OD-DEAL: Dynamic Expert-Guided Adversarial Learning with Online Decomposition for Scalable Capacitated Vehicle Routing
Jiao, Dongbin
Chen, Zisheng
Wang, Xianyi
Shi, Jintao
Liu, Shengcai
Yan, Shi
Machine Learning
Solving large-scale capacitated vehicle routing problems (CVRP) is hindered by the high complexity of heuristics and the limited generalization of neural solvers on massive graphs. We propose OD-DEAL, an adversarial learning framework that tightly integrates hybrid genetic search (HGS) and online barycenter clustering (BCC) decomposition, and leverages high-fidelity knowledge distillation to transfer expert heuristic behavior. OD-DEAL trains a graph attention network (GAT)-based generative policy through a minimax game, in which divide-and-conquer strategies from a hybrid expert are distilled into dense surrogate rewards. This enables high-quality, clustering-free inference on large-scale instances. Empirical results demonstrate that OD-DEAL achieves state-of-the-art (SOTA) real-time CVRP performance, solving 10000-node instances with near-constant neural scaling. This uniquely enables the sub-second, heuristic-quality inference required for dynamic large-scale deployment.
title OD-DEAL: Dynamic Expert-Guided Adversarial Learning with Online Decomposition for Scalable Capacitated Vehicle Routing
topic Machine Learning
url https://arxiv.org/abs/2602.00488