Robust Federated Learning with Noisy Labels

TL;DR

This paper proposes a novel federated learning method that maintains consistent decision boundaries across clients with noisy labels by exchanging class-wise centroids, and improves local model performance through confident sample selection and pseudo-labeling.

Contribution

It introduces a server-assisted centroid alignment scheme and a global-guided pseudo-labeling approach to address noisy labels in federated learning, which are novel contributions.

Findings

Effective on noisy CIFAR-10 dataset.

Improves model consistency across clients.

Enhances local model accuracy with pseudo-labeling.

Abstract

Federated learning is a paradigm that enables local devices to jointly train a server model while keeping the data decentralized and private. In federated learning, since local data are collected by clients, it is hardly guaranteed that the data are correctly annotated. Although a lot of studies have been conducted to train the networks robust to these noisy data in a centralized setting, these algorithms still suffer from noisy labels in federated learning. Compared to the centralized setting, clients' data can have different noise distributions due to variations in their labeling systems or background knowledge of users. As a result, local models form inconsistent decision boundaries and their weights severely diverge from each other, which are serious problems in federated learning. To solve these problems, we introduce a novel federated learning scheme that the server cooperates with local models to maintain consistent decision boundaries by interchanging class-wise centroids. These centroids are central features of local data on each device, which are aligned by the server every communication round. Updating local models with the aligned centroids helps to form consistent decision boundaries among local models, although the noise distributions in clients' data are different from each other. To improve local model performance, we introduce a novel approach to select confident samples that are used for updating the model with given labels. Furthermore, we propose a global-guided pseudo-labeling method to update labels of unconfident samples by exploiting the global model. Our experimental results on the noisy CIFAR-10 dataset and the Clothing1M dataset show that our approach is noticeably effective in federated learning with noisy labels.