arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.00312cs.AIcs.NE
收藏

UDC:面向大规模组合优化问题的统一神经分治框架

UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems

School of System Design and Intelligent Manufacturing, Southern University of Science and Technology(南方科技大学系统设计与智能制造学院);Huawei Noah’s Ark Lab(华为诺亚方舟实验室)

Zhi Zheng, Changliang Zhou, Tong Xialiang, Mingxuan Yuan, Zhenkun Wang

AI总结:

本文提出统一神经分治框架UDC,通过分治-重聚训练和GNN划分及固定长度子路径求解器,解决大规模组合优化问题,在10个代表性问题上表现优越。

摘要:

单阶段神经组合优化求解器已在各种小规模组合优化(CO)问题上取得了接近最优的结果,且无需专家知识。然而,这些求解器在应用于大规模CO问题时表现出显著的性能退化。近年来,受分治策略启发的两阶段神经方法在解决大规模CO问题方面显示出高效性。然而,这些方法的性能高度依赖于划分或征服过程中的问题特定启发式方法,这限制了它们对一般CO问题的适用性。此外,这些方法采用分离的训练方案,忽略了划分与征服策略之间的相互依赖关系,常常导致次优解。为解决这些缺陷,本文开发了一个统一的神经分治框架(即UDC),用于求解一般的大规模CO问题。UDC提供了一种分治-重聚(DCR)训练方法,以消除次优划分策略的负面影响。所提出的UDC框架采用高效图神经网络(GNN)进行全局实例划分,并使用固定长度的子路径求解器来征服划分后的子问题,展现出广泛的适用性,在10个代表性的大规模CO问题上取得了优越的性能。代码可在https://github.com/CIAM-Group/NCO_code/tree/main/single_objective/UDC-Large-scale-CO-master获取。

英文摘要:

Single-stage neural combinatorial optimization solvers have achieved near-optimal results on various small-scale combinatorial optimization (CO) problems without requiring expert knowledge. However, these solvers exhibit significant performance degradation when applied to large-scale CO problems. Recently, two-stage neural methods motivated by divide-and-conquer strategies have shown efficiency in addressing large-scale CO problems. Nevertheless, the performance of these methods highly relies on problem-specific heuristics in either the dividing or the conquering procedure, which limits their applicability to general CO problems. Moreover, these methods employ separate training schemes and ignore the interdependencies between the dividing and conquering strategies, often leading to sub-optimal solutions. To tackle these drawbacks, this article develops a unified neural divide-and-conquer framework (i.e., UDC) for solving general large-scale CO problems. UDC offers a Divide-Conquer-Reunion (DCR) training method to eliminate the negative impact of a sub-optimal dividing policy. Employing a high-efficiency Graph Neural Network (GNN) for global instance dividing and a fixed-length sub-path solver for conquering divided sub-problems, the proposed UDC framework demonstrates extensive applicability, achieving superior performance in 10 representative large-scale CO problems. The code is available at https://github.com/CIAM-Group/NCO_code/tree/main/single_objective/UDC-Large-scale-CO-master.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑