FedSPU: Personalized Federated Learning for Resource-constrained Devices with Stochastic Parameter Update

arXiv:2403.11464v1 Announce Type: new
Abstract: Personalized Federated Learning (PFL) is widely employed in IoT applications to handle high-volume, non-iid client data while ensuring data privacy. However, heterogeneous edge devices owned by clients may impose varying degrees of resource constraints, causing computation and communication bottlenecks for PFL. Federated Dropout has emerged as a popular strategy to address this challenge, wherein only a subset of the global model, i.e. a \textit{sub-model}, is trained on a client's device, thereby reducing computation and communication …

abstract applications arxiv bottlenecks client communication computation constraints cs.lg data data privacy devices dropout edge edge devices federated learning however iot personalized privacy stochastic type update