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 2207.13667cs.LG
收藏

神经元TSP求解器的无监督训练

Unsupervised Training for Neural TSP Solver

University of Latvia(拉脱维亚大学);Institute of Mathematics and Computer Science at University of Latvia(拉脱维亚大学数学与计算机科学研究所);Institute of Electronics and Computer Science(电子与计算机科学研究所)

Elīza Gaile, Andis Draguns, Emīls Ozoliņš, Kārlis Freivalds

摘要:

已经有越来越多的机器学习方法来近似解决旅行商问题。然而,这些方法通常需要解决的训练实例或使用复杂的强化学习方法,需要大量的调整。为了避免这些问题,我们引入了一种新的无监督学习方法。我们使用一个整数线性规划的TSP松弛构造一个损失函数,不需要正确的实例标签。在变量离散化的情况下,其最小值与最优解或近似最优解一致。此外,该损失函数是可微的,因此可以直接用于训练神经网络。我们使用我们的损失函数与图神经网络和设计控制实验上的欧几里德和非对称TSP。与监督学习相比,我们的方法具有不需要大型标记数据集的优势。此外,我们的方法的性能超过强化学习的非对称TSP和欧几里德实例的强化学习。我们的方法也比强化学习更稳定,更容易训练。

英文摘要:

There has been a growing number of machine learning methods for approximately solving the travelling salesman problem. However, these methods often require solved instances for training or use complex reinforcement learning approaches that need a large amount of tuning. To avoid these problems, we introduce a novel unsupervised learning approach. We use a relaxation of an integer linear program for TSP to construct a loss function that does not require correct instance labels. With variable discretization, its minimum coincides with the optimal or near-optimal solution. Furthermore, this loss function is differentiable and thus can be used to train neural networks directly. We use our loss function with a Graph Neural Network and design controlled experiments on both Euclidean and asymmetric TSP. Our approach has the advantage over supervised learning of not requiring large labelled datasets. In addition, the performance of our approach surpasses reinforcement learning for asymmetric TSP and is comparable to reinforcement learning for Euclidean instances. Our approach is also more stable and easier to train than reinforcement learning.

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。

↑