arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.01227cs.LGstat.ML
收藏

求解旅行商问题的一种有效的图卷积网络技术

An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem

Nanyang Technological University(南洋理工大学);Loyola Marymount University(洛约拉马利蒙特大学)

Chaitanya K. Joshi, Thomas Laurent, Xavier Bresson

摘要:

本文介绍了一种新的基于学习的方法近似解决旅行商问题的二维欧几里德图。我们使用深度图卷积网络来构建高效的TSP图表示,并通过高度并行化的束搜索以非自回归方式输出旅游。我们的方法在解决方案质量、推理速度和固定图大小的问题实例的样本效率方面优于所有最近提出的自回归深度学习技术。特别是,对于50个节点,我们将平均最优性差距从0.52%减少到0.01%,对于100个节点,我们将平均最优性差距从2.26%减少到1.39%。最后,尽管对TSP的其他基于学习的方法进行了改进,但我们的方法与标准的运筹学求解器相比仍有差距。

英文摘要:

This paper introduces a new learning-based approach for approximately solving the Travelling Salesman Problem on 2D Euclidean graphs. We use deep Graph Convolutional Networks to build efficient TSP graph representations and output tours in a non-autoregressive manner via highly parallelized beam search. Our approach outperforms all recently proposed autoregressive deep learning techniques in terms of solution quality, inference speed and sample efficiency for problem instances of fixed graph sizes. In particular, we reduce the average optimality gap from 0.52% to 0.01% for 50 nodes, and from 2.26% to 1.39% for 100 nodes. Finally, despite improving upon other learning-based approaches for TSP, our approach falls short of standard Operations Research solvers.

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。

↑