arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.10658cs.LG
收藏

将小的预训练模型推广到非常大的TSP模型

Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances

Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳市人工智能与机器人研究院);Institute of Robotics and Intelligent Manufacturing, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)机器人与智能制造研究院);School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院)

Zhang-Hua Fu, Kai-Bin Qiu, Hongyuan Zha

摘要:

对于旅行商问题(TSP),现有的基于监督学习的算法普遍存在泛化能力不足的问题。为了克服这一缺点,本文尝试通过图采样、图转换和热图合并等技术,以监督的方式训练一个小规模的模型,该模型可以重复用于构建任意大规模TSP实例的热图。此外,热图被馈送到强化学习方法(蒙特卡罗树搜索)中,以指导高质量解决方案的搜索。基于大量实例(最多10,000个顶点)的实验结果表明,该方法明显优于现有的基于机器学习的TSP算法,并显著提高了训练模型的泛化能力。

英文摘要:

For the traveling salesman problem (TSP), the existing supervised learning based algorithms suffer seriously from the lack of generalization ability. To overcome this drawback, this paper tries to train (in supervised manner) a small-scale model, which could be repetitively used to build heat maps for TSP instances of arbitrarily large size, based on a series of techniques such as graph sampling, graph converting and heat maps merging. Furthermore, the heat maps are fed into a reinforcement learning approach (Monte Carlo tree search), to guide the search of high-quality solutions. Experimental results based on a large number of instances (with up to 10,000 vertices) show that, this new approach clearly outperforms the existing machine learning based TSP algorithms, and significantly improves the generalization ability of the trained model.

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。

↑