# Decision-Focused Continual Learning for Seaport Power-Logistics Scheduling: Generalization across Varying Tasks

arXiv: https://arxiv.org/abs/2511.07938 · HTML: https://mlsanity.com/paper/2511.07938/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 44 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [OptNet: Differentiable Optimization as a Layer in Neural Networks](https://mlsanity.com/paper/1703.00443/) (2017)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities](https://mlsanity.com/paper/2307.13565/) (2023)
- [A bilevel framework for decision-making under uncertainty with contextual information](https://mlsanity.com/paper/2008.01500/) (2020)
- [LfEdNet: A Task-based Day-ahead Load Forecasting Model for Stochastic Economic Dispatch](https://mlsanity.com/paper/2008.07025/) (2020)
- [Electricity Price Prediction for Energy Storage System Arbitrage: A Decision-focused Approach](https://mlsanity.com/paper/2305.00362/) (2023)
- [Perturbed Decision-Focused Learning for Modeling Strategic Energy Storage](https://mlsanity.com/paper/2406.17085/) (2024)
- [Same accuracy, twice as fast: continuous training surpasses retraining from scratch](https://mlsanity.com/paper/2502.21147/) (2025)
- [Effective End-to-End Learning Framework for Economic Dispatch](https://mlsanity.com/paper/2002.12755/) (2020)
- [Multi-Task Predict-then-Optimize](https://mlsanity.com/paper/2212.05403/) (2022)
- [Safety-aware Semi-end-to-end Coordinated Decision Model for Voltage Regulation in Active Distribution Network](https://mlsanity.com/paper/2305.15395/) (2023)
- [Load Data Valuation in Multi-Energy Systems: An End-to-End Approach](https://mlsanity.com/paper/2311.09839/) (2023)
- [Predict-and-Optimize Robust Unit Commitment with Statistical Guarantees via Weight Combination](https://mlsanity.com/paper/2411.03138/) (2024)
- [E2E-AT: A Unified Framework for Tackling Uncertainty in Task-aware End-to-end Learning](https://mlsanity.com/paper/2312.10587/) (2023)
- [End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty](https://mlsanity.com/paper/2402.07772/) (2024)
- [A Weighted Predict-and-Optimize Framework for Power System Operation Considering Varying Impacts of Uncertainty](https://mlsanity.com/paper/2503.11001/) (2025)
- [A Hybrid Strategy for Probabilistic Forecasting and Trading of Aggregated Wind-Solar Power: Design and Analysis in HEFTCom2024](https://mlsanity.com/paper/2505.10367/) (2025)
- [Risk-Aware Objective-Based Forecasting in Inertia Management](https://mlsanity.com/paper/2303.11785/) (2023)
- [Adaptive Decision-Objective Loss for Forecast-then-Optimize in Power Systems](https://mlsanity.com/paper/2312.13501/) (2023)
- [DFF: Decision-Focused Fine-tuning for Smarter Predict-then-Optimize with Limited Data](https://mlsanity.com/paper/2501.01874/) (2025)

## Abstract (arXiv)

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.