用特征谱结构识别并重标联邦学习中的噪声标签，提升模型鲁棒性。
FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels
- 通过分析特征子空间的谱一致性，低开销识别干净与噪声客户端。
- 利用干净客户端的谱参考，指导噪声样本的重标注。
- 融合对数调整损失、知识蒸馏与距离感知聚合，稳定优化过程。
联邦学习（FL）可在不共享原始数据的情况下实现协作模型训练，但分布式客户端中的标签噪声会严重降低学习性能。本文提出FedSIR，一种针对标签噪声的鲁棒联邦学习多阶段框架。不同于以往依赖噪声容忍损失函数或训练过程中的损失动态的方法，本方法利用客户端特征表示的谱结构来识别并缓解标签噪声。框架包含三个核心组件：首先，通过分析类别特征子空间的谱一致性，在极低通信开销下识别干净与噪声客户端；其次，干净客户端提供谱参考，使噪声客户端能基于主类方向和残差子空间对潜在污染样本进行重标注；第三，采用噪声感知训练策略，结合对数调整损失、知识蒸馏与距离感知聚合，进一步稳定联邦优化。在标准联邦学习基准上的大量实验表明，FedSIR在多种噪声场景下均显著优于现有最先进方法。代码已开源：https://github.com/sinagh72/FedSIR。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。