FedTrans: Efficient Federated Learning Over Heterogeneous Clients via Model Transformation

arXiv:2404.13515v1 Announce Type: new
Abstract: Federated learning (FL) aims to train machine learning (ML) models across potentially millions of edge client devices. Yet, training and customizing models for FL clients is notoriously challenging due to the heterogeneity of client data, device capabilities, and the massive scale of clients, making individualized model exploration prohibitively expensive. State-of-the-art FL solutions personalize a globally trained model or concurrently train multiple models, but they often incur suboptimal model accuracy and huge training costs.
In this …

abstract arxiv capabilities client cs.ai cs.dc cs.lg data devices edge federated learning machine machine learning making massive scale train training transformation type via