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 2407.17206cs.LGcs.AI
收藏

迈出一步再重新考量:面向自改进神经组合优化的序列解码

Take a Step and Reconsider: Sequence Decoding for Self-Improved Neural Combinatorial Optimization

Technical University of Munich(慕尼黑工业大学);University of Applied Sciences Weihenstephan-Triesdorf(魏恩施蒂芬-特里斯多夫应用科学大学)

Jonathan Pirnay, Dominik G. Grimm

AI总结:

针对神经组合优化自改进学习中伪标签质量依赖策略解获取方式的问题,提出基于无放回采样的通用序列解码方法,通过从中间解重启采样、屏蔽已采样序列提升多样性,在多个经典组合优化问题上取得优于现有NCO方法的性能。

摘要:

神经组合优化(Neural Combinatorial Optimization, NCO)中的构造式方法将组合优化问题视为有限马尔可夫决策过程,在神经策略网络的引导下通过一系列决策逐步构建解。为训练该策略,近期研究正转向一种“自改进”学习方法,以解决强化学习和监督式方法的局限性。在该方法中,策略以监督方式迭代训练,由当前策略生成的解充当伪标签,而从策略中获取这些解的方式决定了伪标签的质量。本文提出一种简单且与问题无关的自改进学习序列解码方法,该方法基于无放回采样序列。我们沿着已找到的最优解逐步推进,并从中间部分解重启采样过程。通过修改策略使其忽略已采样的序列,我们强制策略仅考虑未见过的备选方案,从而提升解的多样性。在旅行商问题(Traveling Salesman Problem)和带容量约束的车辆路径问题(Capacitated Vehicle Routing Problem)上的实验结果证明了该方法的优异性能。此外,我们的方法在作业车间调度问题(Job Shop Scheduling Problem)上优于已有的NCO方法。

英文摘要:

The constructive approach within Neural Combinatorial Optimization (NCO) treats a combinatorial optimization problem as a finite Markov decision process, where solutions are built incrementally through a sequence of decisions guided by a neural policy network. To train the policy, recent research is shifting toward a 'self-improved' learning methodology that addresses the limitations of reinforcement learning and supervised approaches. Here, the policy is iteratively trained in a supervised manner, with solutions derived from the current policy serving as pseudo-labels. The way these solutions are obtained from the policy determines the quality of the pseudo-labels. In this paper, we present a simple and problem-independent sequence decoding method for self-improved learning based on sampling sequences without replacement. We incrementally follow the best solution found and repeat the sampling process from intermediate partial solutions. By modifying the policy to ignore previously sampled sequences, we force it to consider only unseen alternatives, thereby increasing solution diversity. Experimental results for the Traveling Salesman and Capacitated Vehicle Routing Problem demonstrate its strong performance. Furthermore, our method outperforms previous NCO approaches on the Job Shop Scheduling Problem.

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。

↑