AI RESEARCH

FedScalar: Federated Learning with Scalar Communication for Bandwidth-Constrained Networks

arXiv CS.LG

ArXi:2410.02260v3 Announce Type: replace In bandwidth-constrained federated learning~(FL) settings, the repeated upload of high-dimensional model updates from agents to a central server constitutes the primary bottleneck, often rendering standard FL infeasible within practical communication budgets. We propose \emph{FedScalar}, a communication-efficient FL algorithm in which each agent uploads only two scalar values per round, regardless of the model dimension~$d