FedCRL: Personalized Federated Learning with Contrastive Shared Representations for Label Heterogeneity in Non-IID Data

arXiv:2404.17916v1 Announce Type: new
Abstract: To deal with heterogeneity resulting from label distribution skew and data scarcity in distributed machine learning scenarios, this paper proposes a novel Personalized Federated Learning (PFL) algorithm, named Federated Contrastive Representation Learning (FedCRL). FedCRL introduces contrastive representation learning (CRL) on shared representations to facilitate knowledge acquisition of clients. Specifically, both local model parameters and averaged values of local representations are considered as shareable information to the server, both of which are then aggregated globally. CRL …

abstract algorithm arxiv cs.ai cs.lg data deal distributed distribution federated learning machine machine learning novel paper personalized representation representation learning skew type