SOURCE-LINKED INTELLIGENCE

Distributionally Robust Federated Learning with Multi-Source Data

arXiv · AI, language, vision and robotics · article · Sep 17, 2026 · UTC

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 s

Read original source ↗ Open in workspace

recordType

paper

region

Global