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

• URL: http://arxiv.org/abs/2604.20825v1
• Date: Wed, 22 Apr 2026 17:49:20 GMT
• Title: FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels
• Abstract summary: Federated learning (FL) enables collaborative model training without sharing raw data.<n>The presence of noisy labels across distributed clients can severely degrade the learning performance.<n>We propose FedSIR, a multi-stage framework for robust FL under noisy labels.
• Score: 2.0878272814614087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• FNBench: Benchmarking Robust Federated Learning against Noisy Labels [23.660857480962104]
  This paper presents the first benchmark study on noisy labels in federated learning (FL)<n>We consider three diverse label noise patterns covering synthetic label noise, imperfect human-annotation errors and systematic errors.<n>Our evaluation incorporates eighteen state-of-the-art methods over five image recognition datasets and one text classification dataset.
  arXiv  Detail & Related papers  (2025-05-10T16:14:52Z)
• Federated Learning Client Pruning for Noisy Labels [6.30126491637621]
  Federated Learning (FL) enables collaborative model training across decentralized edge devices. This paper introduces ClipFL, a novel framework addressing noisy labels from a fresh perspective. It identifies and excludes noisy clients based on their performance on a clean validation dataset.
  arXiv  Detail & Related papers  (2024-11-11T21:46:34Z)
• Federated Learning with Extremely Noisy Clients via Negative Distillation [70.13920804879312]
  Federated learning (FL) has shown remarkable success in cooperatively training deep models, while struggling with noisy labels. We propose a novel approach, called negative distillation (FedNed) to leverage models trained on noisy clients. FedNed first identifies noisy clients and employs rather than discards the noisy clients in a knowledge distillation manner.
  arXiv  Detail & Related papers  (2023-12-20T01:59:48Z)
• FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels [99.70895640578816]
  Federated learning with noisy labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning. We present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter.
  arXiv  Detail & Related papers  (2023-12-19T15:46:47Z)
• FedNoisy: Federated Noisy Label Learning Benchmark [53.73816587601204]
  Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients.<n>The distributed and isolated nature of data isolation may be complicated by data quality, making it more vulnerable to noisy labels.<n>We serve the first standardized benchmark that can help researchers fully explore potential federated noisy settings.
  arXiv  Detail & Related papers  (2023-06-20T16:18:14Z)
• Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients [4.782145666637457]
  Federated learning (FL) is a distributed framework for collaboratively training with privacy guarantees. In real-world scenarios, clients may have Non-IID data (local class imbalance) with poor annotation quality (label noise) We propose FedCNI without using an additional clean proxy dataset. It includes a noise-resilient local solver and a robust global aggregator.
  arXiv  Detail & Related papers  (2023-04-06T06:47:14Z)
• Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels [3.4620497416430456]
  Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets. We propose FedLN, a framework to deal with label noise across different FL training stages. Our evaluation on various publicly available vision and audio datasets demonstrate a 22% improvement on average compared to other existing methods for a label noise level of 60%.
  arXiv  Detail & Related papers  (2022-08-19T14:47:40Z)
• FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels [49.47228898303909]
  Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices. Local training on noisy labels can easily result in overfitting to noisy labels, which is devastating to the global model through aggregation. We develop a simple two-level sampling method "FedNoiL" that selects clients for more robust global aggregation on the server.
  arXiv  Detail & Related papers  (2022-05-20T12:06:39Z)
• FedCorr: Multi-Stage Federated Learning for Label Noise Correction [80.9366438220228]
  Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. We propose $textttFedCorr$, a general multi-stage framework to tackle heterogeneous label noise in FL. Experiments conducted on CIFAR-10/100 with federated synthetic label noise, and on a real-world noisy dataset, Clothing1M, demonstrate that $textttFedCorr$ is robust to label noise.
  arXiv  Detail & Related papers  (2022-04-10T12:51:18Z)
• S3: Supervised Self-supervised Learning under Label Noise [53.02249460567745]
  In this paper we address the problem of classification in the presence of label noise. In the heart of our method is a sample selection mechanism that relies on the consistency between the annotated label of a sample and the distribution of the labels in its neighborhood in the feature space. Our method significantly surpasses previous methods on both CIFARCIFAR100 with artificial noise and real-world noisy datasets such as WebVision and ANIMAL-10N.
  arXiv  Detail & Related papers  (2021-11-22T15:49:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.