SOURCE-LINKED INTELLIGENCE

FedRAW: Preserving Rare-Label Influence in Asynchronous Federated Learning

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Asynchronous federated learning improves scalability by updating the global model from a server-side buffer of client updates as they arrive, rather than waiting for all selected clients to finish. While efficient, this arrival-driven aggregation can silently distort representation learning under heterogeneous participation. We identify silent rarity failure, a hidden failure mode in which clients holding rare labels contribute too weakly to the global model even though its overall accuracy appears largely unaffected. This failure arises from two coupled effects: rare-label clients may submit

Read original source ↗ Open in workspace

recordType

paper

region

Global