Topology Learning for Heterogeneous Decentralized Federated Learning over Unreliable D2D Networks

arXiv:2312.13611v2 Announce Type: replace
Abstract: With the proliferation of intelligent mobile devices in wireless device-to-device (D2D) networks, decentralized federated learning (DFL) has attracted significant interest. Compared to centralized federated learning (CFL), DFL mitigates the risk of central server failures due to communication bottlenecks. However, DFL faces several challenges, such as the severe heterogeneity of data distributions in diverse environments, and the transmission outages and package errors caused by the adoption of the User Datagram Protocol (UDP) in D2D networks. These …

abstract arxiv bottlenecks challenges communication cs.lg cs.ni decentralized devices eess.sp federated learning however intelligent mobile mobile devices networks risk server topology type wireless