cs.LGNov 15, 2026

Communication-Efficient Distributionally Robust Federated Averaging with Multi-Source Data

Authors: Yingzhu Liu, Zhongkui Li, Pengcheng You, Ashish Cherukuri

Organizations: Department of Control Science and Systems Engineering, Peking University · Engineering and Technology Institute Groningen, University of Groningen

Abstract

Federated learning trains a shared model from distributed client data. The deployment risk is typically specified through two approximations: each unknown local distribution is replaced by its empirical distribution, and the unknown deployment mixture across clients is replaced by empirical or prescribed training weights. Existing robust methods usually address one approximation at a time through local distributional ambiguity sets or worst-case client mixtures. However, joint treatment of both approximations remains underexplored. To address this gap, we construct a global ambiguity set formed by admissible mixtures of client-wise Wasserstein ambiguity sets, yielding a distributionally robust optimization formulation. The construction allows client-dependent ambiguity radii, preserves client-wise separability of the objective function, and yields a high-probability out-of-sample guarantee for the resulting robust problem. We then introduce a penalty-based approximation of this formulation and develop a communication-efficient algorithm called BiDRO-FedAvg, for which we establish a convergence guarantee. We validate the proposed framework through a market-demand prediction simulation.

Figures & tables

Explore similar work

CardsList
  1. Distributionally Robust Federated Learning with Multi-Source Data

    Sep 17, 2026Yingzhu Liu, Zhongkui Li, Pengcheng You +1Distributionally Robust OptimizationNon-IID Federated Learning

  2. Enhancing Robustness of Federated Learning via Server Learning

    Apr 3, 2026Van Sy Mai, Kushal Chakrabarti, Richard J. La +1Federated LearningByzantine-Robust Federated Learning