IEEE

Staleness-aware Semi-Asynchronous Federated Learning with Adaptive Learning Rates and Non-IID Data in Edge Networks

Abstract: Amidst the diverse computational and communication capabilities of the resource-constrained edge devices (EDs), synchronous model aggregation in wireless federated learning (FL) often ...
IEEE

FedDPSA: A Robust Semi-Asynchronous Differentially Private Federated Learning Framework in Heterogeneous Environments

Abstract: Federated Learning (FL) is a distributed framework that shares local model parameters to reduce privacy leakage. However, performance disparities across devices and the non-IID data ...