Distributionally Robust Federated Learning with Multi-Source Data

2026-09-17

AI Summary

本文针对联邦学习中跨客户端混合不确定性和客户端内分布模糊性问题，通过构建全局模糊集合并提出基于惩罚的联邦算法来解决。

Abstract

Federated learning trains a shared model from private client data. In practice, data-generating distributions may differ, and the true mixture across clients is often unknown, making the underlying group distribution difficult to specify. Existing approaches address cross-client mixture uncertainty by optimizing against the worst-case mixture, yet assume accurate client-wise distribution estimates. However, these estimates can be unreliable when based on finite samples. To handle both cross-client mixture uncertainty and within-client distributional ambiguity, we construct a global ambiguity set as the union of admissible mixtures of local ambiguity sets. The construction allows client-specific ambiguity radii and admits a client-wise separable reformulation. Leveraging this structure, we establish a high-probability out-of-sample performance guarantee. We further develop a federated algorithm for a penalty-based reformulation and prove its convergence under milder regularity conditions. Simulations validate the algorithm's effectiveness.

Problem

• Federated Learning
• Distributional Robustness
• Multi-Source Data
• Ambiguity Set
• Cross-Client Mixture

Innovation

• Distributionally Robust Federated Learning
• Global Ambiguity Set
• Client-Specific Ambiguity Radii
• Out-of-Sample Performance Guarantee
• Federated Algorithm