FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning
This addresses robustness issues in federated learning for applications with noisy client data, representing an incremental advance over existing methods.
The paper tackles the challenge of noisy labels and data heterogeneity in federated learning by proposing FedRN, which selects reliable neighbors to train on clean examples, resulting in significant improvements in test accuracy on benchmark datasets.
Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels. However, it is far more complex and challenging owing to varying levels of data heterogeneity and noise over clients, which exacerbates the client-to-client performance discrepancy. In this work, we propose a robust federated learning method called FedRN, which exploits k-reliable neighbors with high data expertise or similarity. Our method helps mitigate the gap between low- and high-performance clients by training only with a selected set of clean examples, identified by their ensembled mixture models. We demonstrate the superiority of FedRN via extensive evaluations on three real-world or synthetic benchmark datasets. Compared with existing robust training methods, the results show that FedRN significantly improves the test accuracy in the presence of noisy labels.