SOURCE-LINKED INTELLIGENCE

Beyond Non-IID: Learner--Client Distribution Mismatch in Federated Learning

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Federated learning systems are increasingly deployed to facilitate collaborative model training across a heterogeneous client population. Existing practice mostly implicitly assumes that the aggregated client data distribution is representative of the learner's target distribution or that learning from all available clients is uniformly beneficial for the learner distribution. However, such an assumption often does not hold in reality. Traditional client selection strategies in FL literature largely overlook such misalignment, while most existing work on multi-source transfer learning either r

Read original source ↗ Open in workspace

recordType

paper

region

Global