发表机构
Auburn University（奥本大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对跨孤岛场景下决策聚焦联邦学习中的目标与可行集异构性问题，提出基于正则化投影平滑的FedRSPO+框架，并证明其决策误差界与跨客户端异构性界，实验验证平滑策略的有效性。
AI 中文摘要
决策聚焦学习（DFL）训练预测模型以用于下游优化，但现有方法大多假设数据集中式存储。在跨孤岛（cross-silo）场景中，联邦学习提供了一种自然的替代方案，然而标准联邦方法优化的是预测质量而非决策质量，并且未处理下游目标或可行集中的异构性。这种异构性对DFL尤其具有挑战性，因为多面体问题中的微小扰动可能导致最优决策发生不连续变化，从而破坏客户端更新和聚合的稳定性。我们提出FedRSPO+，一种面向决策聚焦联邦学习的异构感知框架，它基于RSPO+构建，RSPO+是一种通过投影平滑决策映射的正则化预测-然后-优化（predict-then-optimize）代理。我们证明RSPO+在正则化决策上界定了决策误差和遗憾，并且在精确正则化和一致的LP解选择下，对原始LP决策也成立。我们进一步推导了跨客户端异构性界，该界同时依赖于目标异构性和可行集异构性，在同质情况下消失，且不需要强凸性。FedRSPO+采用退火模块化训练流程，与标准联邦个性化和聚合方法兼容。在合成背包、最短路径和真实世界能源定价任务上的实验，与仅预测的联邦学习和DFL基线在不同异构性和通信预算下进行了比较。结果表明，平滑是稳定协作决策学习的有用成分，并为联邦DFL提供了异构感知基础。
英文摘要
Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data. In cross-silo settings, federated learning offers a natural alternative, yet standard federated methods optimize prediction over decision quality and do not address heterogeneity in downstream objectives or feasible sets. This heterogeneity is especially challenging for DFL because small perturbations in polyhedral problems can cause discontinuous changes in optimal decisions, destabilizing client updates and aggregation. We propose FedRSPO+, a heterogeneity-aware framework for decision-focused federated learning, built on RSPO+, a regularized predict-then-optimize surrogate that smooths the decision map through projection. We show that RSPO+ upper bounds decision error and regret for the regularized decision and, under exact regularization and consistent LP solution selection, for the original LP decision. We further derive cross-client heterogeneity bounds that depend on both objective and feasible-set heterogeneity, vanish at homogeneity, and require no strong convexity. FedRSPO+ uses an annealed, modular training procedure compatible with standard federated personalization and aggregation methods. Experiments on synthetic knapsack, shortest-path, and real-world energy pricing tasks compare against prediction-only federated learning and DFL baselines under varying heterogeneity and communication budgets. Results suggest that smoothing is a useful ingredient for stable collaborative decision learning and provide a heterogeneity-aware foundation for federated DFL.
Comments10 pages main paper + appendix. Accepted at NeurIPS 2026 main track
