SOURCE-LINKED INTELLIGENCE

FedeRage: Provably Convergent Agnostic Federated Learning under General Client Drift

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

Federated learning (FL) enables collaborative model training without sharing raw data, but its performance degrades under non-IID data and stochastic client participation. Remedies built on classical Federated Averaging (FedAvg) typically presuppose that client participation probabilities are known to the server, which is rarely the case in deployed systems. We first discuss and then characterize the optimization problem that \emph{distributionally agnostic} FedAvg actually solves when participation is entirely unknown, possibly highly skewed, and of variable size across rounds: uniform aggreg

Read original source ↗ Open in workspace

recordType

paper

region

Global