arXiv：cs.LG· Konstantinos Ziliaskopoulos, Alexander Vinel, Jiaqi Wang·· 3 小时前AI 评分34
FedRSPO+：面向决策聚焦联邦学习的异质性感知算法
FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning
AI 导读
FedRSPO+ 是面向决策聚焦联邦学习的异质性感知框架，基于正则化代理 RSPO+，通过投影平滑决策映射。该研究证明了 RSPO+ 对正则化决策及原 LP 决策的决策误差与 regret 上界，并推导出依赖目标与可行集异质性的跨客户端界限，无需强凸性。
正文
Abstract: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.
| Comments: | 10 pages main paper + appendix. Accepted at NeurIPS 2026 main track |
| Subjects: | Machine Learning (cs.LG); Optimization and Control (math.OC); Machine Learning (stat.ML) |
| Cite as: | arXiv:2610.09091 [cs.LG] |
| (or arXiv:2610.09091v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09091 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Konstantinos Ziliaskopoulos [view email]
[v1]
Tue, 6 Oct 2026 20:46:01 UTC (570 KB)
来源：arXiv：cs.LG · arxiv.org