持续练习与精炼：在持续漂移任务下的终身学习车辆路径问题
Keep Rehearsing and Refining: Lifelong Learning Vehicle Routing under Continually Drifting Tasks
AI总结：
本文提出了一种应对持续漂移任务的终身学习方法，通过Dual Replay with Experience Enhancement框架提升学习效率并缓解灾难性遗忘。
摘要：
现有神经网络求解车辆路径问题（VRP）通常在固定任务集上一次性训练或在任务连续到达时进行终身学习，假设每个任务有足够的训练资源。这两种方法忽略了现实中的一个共同特性：问题模式可能随时间持续漂移，导致大量任务依次出现，每个任务仅有有限的训练资源。本文提出了一种新的终身学习范式，用于在时间持续漂移的任务下神经VRP求解器，其中每个任务在学习时间步中是局部稳定的，但仅接收有限的训练资源。我们通过现实物流数据集实证表明这种持续漂移在实践中存在。然后我们提出Dual Replay with Experience Enhancement（DREE），一种通用框架，用于在这样的漂移下提高学习效率并缓解灾难性遗忘。基于现实物流数据集和常用合成数据集的广泛实验表明，在这种持续漂移下，DREE能够有效学习新任务，保留先前知识，提高对未见过任务的泛化能力，并可应用于各种现有神经求解器。
英文摘要：
Existing neural solvers for vehicle routing problems (VRPs) are typically trained either in a one-off manner on a fixed set of pre-defined tasks or in a lifelong manner with tasks arriving sequentially, assuming sufficient training on each task. Both settings overlook a common real-world property: problem patterns may drift continually over time, yielding massive tasks sequentially arising, each with only limited training resources. In this paper, we propose a novel lifelong learning paradigm for neural VRP solvers under continual task drift over time, where each task is locally stationary at one learning time step but receives only insufficient training resources. We empirically demonstrate that such continual drift arises in practice using a real-world logistics dataset. We then propose Dual Replay with Experience Enhancement (DREE), a general framework to improve learning efficiency and mitigate catastrophic forgetting under such drift. Extensive experiments based on both the real-world logistics dataset and commonly used synthetic dataset show that, under such continual drift, DREE effectively learns new tasks, preserves prior knowledge, improves generalization to unseen tasks, and can be applied to various existing neural 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。
