FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning

Key points

• Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data.1
• 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.1
• 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.1
• 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.1

Sources (1)

• [1]FedRSPO+: A Heterogeneity-aware Algorithm for Decision-focused Federated Learning
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 08:46 PM

  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.

  Decision-focused learning (DFL) trains predictive models for downstream optimization, but existing methods largely assume centralized data.

Extractive summary: sentences quoted from the sources.