Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Sidelink-Assisted Data Multicasting Approach

arXiv:2406.09776v1 Announce Type: new
Abstract: Federated Edge Learning (FEEL) emerges as a pioneering distributed machine learning paradigm for the 6G Hyper-Connectivity, harnessing data from the Internet of Things (IoT) devices while upholding data privacy. However, current FEEL algorithms struggle with non-independent and non-identically distributed (non-IID) data, leading to elevated communication costs and compromised model accuracy. To address these statistical imbalances within FEEL, we introduce a clustered data sharing framework, mitigating data heterogeneity by selectively sharing partial data from cluster heads …

abstract algorithms arxiv connectivity convergence cs.lg current data data privacy devices distributed edge faster however independent internet internet of things iot machine machine learning paradigm privacy struggle things type while