FedFDP: Federated Learning with Fairness and Differential Privacy

arXiv:2402.16028v1 Announce Type: new
Abstract: Federated learning (FL) is a new machine learning paradigm to overcome the challenge of data silos and has garnered significant attention. However, through our observations, a globally effective trained model may performance disparities in different clients. This implies that the jointly trained models by clients may lead to unfair outcomes. On the other hand, relevant studies indicate that the transmission of gradients or models in federated learning can also give rise to privacy leakage issues, …

arxiv attention challenge clients cs.cr data data silos differential privacy fairness federated federated learning machine machine learning may paradigm performance privacy silos