Client-supervised Federated Learning: Towards One-model-for-all Personalization

arXiv:2403.19499v1 Announce Type: new
Abstract: Personalized Federated Learning (PerFL) is a new machine learning paradigm that delivers personalized models for diverse clients under federated learning settings. Most PerFL methods require extra learning processes on a client to adapt a globally shared model to the client-specific personalized model using its own local data. However, the model adaptation process in PerFL is still an open challenge in the stage of model deployment and test time. This work tackles the challenge by proposing …

abstract adapt arxiv client cs.lg data diverse extra federated learning however machine machine learning paradigm personalization personalized processes type