FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels

TL;DR

FedSIR introduces a spectral analysis-based framework for robust federated learning with noisy labels, effectively identifying and relabeling corrupted data across clients to improve model accuracy.

Contribution

The paper proposes a novel spectral client identification and relabeling method for federated learning with noisy labels, surpassing existing noise-tolerant approaches.

Findings

FedSIR outperforms state-of-the-art methods on standard benchmarks.

Spectral analysis effectively identifies clean and noisy clients.

Relabeling using spectral references improves training stability.

Abstract

Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can severely degrade the learning performance. In this paper, we propose FedSIR, a multi-stage framework for robust FL under noisy labels. Different from existing approaches that mainly rely on designing noise-tolerant loss functions or exploiting loss dynamics during training, our method leverages the spectral structure of client feature representations to identify and mitigate label noise. Our framework consists of three key components. First, we identify clean and noisy clients by analyzing the spectral consistency of class-wise feature subspaces with minimal communication overhead. Second, clean clients provide spectral references that enable noisy clients to relabel potentially corrupted samples using both dominant class directions and residual subspaces. Third, we employ a noise-aware training strategy that integrates logit-adjusted loss, knowledge distillation, and distance-aware aggregation to further stabilize federated optimization. Extensive experiments on standard FL benchmarks demonstrate that FedSIR consistently outperforms state-of-the-art methods for FL with noisy labels. The code is available at https://github.com/sinagh72/FedSIR.