FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning

arXiv:2403.16561v1 Announce Type: new
Abstract: Federated Learning (FL) heavily depends on label quality for its performance. However, the label distribution among individual clients is always both noisy and heterogeneous. The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches. To tackle this issue, we propose FedFixer, where the personalized model is introduced to cooperate with the global model to effectively …

abstract arxiv challenges client cs.ai cs.lg distribution federated learning however loss noise performance quality samples type