FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity

2023/05/09 by Nannan Wu, Li Yu, Wu, Nannan +7 · 5 citations
Computer Science · #Machine Learning and Data Classification #Imbalanced Data Classification Techniques #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.2305.05230

Abstract

Federated noisy label learning (FNLL) is emerging as a promising tool for privacy-preserving multi-source decentralized learning. Existing research, relying on the assumption of class-balanced global data, might be incapable to model complicated label noise, especially in medical scenarios. In this paper, we first formulate a new and more realistic federated label noise problem where global data is class-imbalanced and label noise is heterogeneous, and then propose a two-stage framework named FedNoRo for noise-robust federated learning. Specifically, in the first stage of FedNoRo, per-class loss indicators followed by Gaussian Mixture Model are deployed for noisy client identification. In the second stage, knowledge distillation and a distance-aware aggregation function are jointly adopted for noise-robust federated model updating. Experimental results on the widely-used ICH and ISIC2019 datasets demonstrate the superiority of FedNoRo against the state-of-the-art FNLL methods for addressing class imbalance and label noise heterogeneity in real-world FL scenarios.

Cited by

• Single-Round Scalable Analytic Federated Learning
• Local K-Similarity Constraint for Federated Learning with Label Noise
• Lightweight and Robust Federated Data Valuation
• Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data
• FNBench: Benchmarking Robust Federated Learning against Noisy Labels
• FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels

Related

• FedCorr: Multi-Stage Federated Learning for Label Noise Correction
• FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels
• Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients
• FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels
• FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning