让港口电力物流调度模型持续学习新任务，还能保持高效与稳定。
Decision-Focused Continual Learning for Seaport Power-Logistics Scheduling: Generalization across Varying Tasks
- 用信息量保留关键参数，提升跨任务泛化能力
- 在新加坡裕廊港实验中表现更好，计算开销更低
- 适合长期动态调度场景的智能系统开发
现代港口的电力-物流调度通常采用先预测后优化的流程。为提升预测对决策的质量影响，决策导向学习被提出，使预测模型训练与下游决策结果对齐。然而，这种端到端设计天然限制了预测模型在任务结构变化时的泛化能力，尤其在船舶到达模式变化时表现不佳。为此，本文提出一种面向决策的持续学习框架，可在线适应调度任务流。具体地，引入基于费舍尔信息的正则化，以保留对先前任务至关重要的参数，增强跨任务泛化；同时设计可微分凸代理函数，稳定梯度反传。该方法实现了在不断变化的任务流中持续学习决策对齐的预测模型，且具备可持续的计算与内存开销。在模拟新加坡裕廊港的数据上验证，相比现有方法，本方法在决策性能、跨任务泛化性方面均有提升，同时降低计算成本并保持固定内存占用。
原文摘要 · Abstract (English)
Power-logistics scheduling in modern seaports typically follows a predict-then-optimize pipeline. To enhance the decision quality of predictions, decision-focused learning has been proposed, which aligns the training of forecasting models with downstream decision outcomes. However, this end-to-end design inherently restricts the value of forecasting models to a specific task structure and therefore generalizes poorly to evolving tasks induced by varying vessel arrivals. We address this gap with a decision-focused continual learning framework that adapts online to a stream of scheduling tasks. Specifically, we introduce Fisher-information-based regularization to enhance cross-task generalization by preserving parameters critical to prior tasks. A differentiable convex surrogate is also developed to stabilize gradient backpropagation. The proposed approach enables learning a decision-aligned forecasting model across a varying task stream with sustainable long-term computational and memory requirements. Experiments calibrated to Jurong Port show improved decision performance and cross-task generalization over existing methods, together with reduced computational cost and a bounded memory footprint.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。