弱监督框架+区域重建，高效求解大规模旅行商问题
LocalEscaper: A Weakly-supervised Framework with Regional Reconstruction for Scalable Neural TSP Solvers
- 结合监督与强化学习优势，用低质量标签数据训练
- 区域重建策略显著提升解的质量，突破局部最优
- 适合需要高效求解大规模组合优化的场景
神经网络求解器在解决旅行商问题（TSP）上展现出巨大潜力，但现有方法面临挑战：监督学习依赖大量高质量标注数据，而强化学习虽减少数据依赖，却效率低下。为此，本文提出 LocalEscaper，一种用于大规模 TSP 的弱监督学习框架。该框架有效融合监督与强化学习优势，可在低质量标签数据上进行有效训练。为进一步提升解的质量，提出区域重建策略，是本文核心方法，可缓解现有局部重建方法中常见的局部最优问题。在合成与真实世界数据集上的实验表明，LocalEscaper 超越现有神经求解器，取得显著成果。
原文摘要 · Abstract (English)
Neural solvers have shown significant potential in solving the Traveling Salesman Problem (TSP), yet current approaches face significant challenges. Supervised learning (SL)-based solvers require large amounts of high-quality labeled data, while reinforcement learning (RL)-based solvers, though less dependent on such data, often suffer from inefficiencies. To address these limitations, we propose LocalEscaper, a novel weakly-supervised learning framework for large-scale TSP. LocalEscaper effectively combines the advantages of both SL and RL, enabling effective training on datasets with low-quality labels. To further enhance solution quality, we introduce a regional reconstruction strategy, which is the key technique of this paper and mitigates the local-optima problem common in existing local reconstruction methods. Experimental results on both synthetic and real-world datasets demonstrate that LocalEscaper outperforms existing neural solvers, achieving remarkable results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。