• Home
  • Search
  • A Static Bi-dimensional Sample Selection for Federated Learning with Label Noise
  • Cite Icon1
  • https://doi.org/10.1007/978-3-031-30637-2_49Copy DOI Icon

A Static Bi-dimensional Sample Selection for Federated Learning with Label Noise

  • Jan 1, 2023
  • Qian Rong +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In real-world Federated learning(FL), client training data may contain label noise, which can harm the generalization performance of the global model. Most existing noisy label learning methods rely on sample selection strategies that treat small-loss samples as correctly labeled ones, and large-loss samples as mislabeled ones. However, large-loss samples may also be valuable hard samples with correct labels. Also, these sample selection strategies have an issue in FL setting: Moreover sample selection strategies require training two models simultaneously and are executed in every mini-batch, which increases the communication cost and client computation. In this paper, we propose an efficient multi-stage federated learning framework to tackle label noise. Firstly, we use self-supervision pre-training to extract category-independent features without using any labels. Secondly, we propose a federated static two-dimensional sample selection(FedSTSS) method, which uses category probability entropy and loss as separation metrics to identify samples. Notably, to improve the accuracy of recognition samples, we add a weight entropy minimization term to the cross-entropy loss function. Finally, we use a semi-supervised method to finetune the global model on identified clean samples and mislabeled samples. Extensive experiments on multiple synthetic and real-world noisy datasets demonstrate that our method outperforms the state-of-the-art methods.

Similar Papers
  • Conference Article
  • Citations106

FedCorr: Multi-Stage Federated Learning for Label Noise Correction

  • Jun 01, 2022
  • Jingyi Xu +3
  • Research Article
  • Citations27

Medical federated learning with joint graph purification for noisy label learning

  • Oct 04, 2023
  • Medical image analysis
  • Zhen Chen +3
  • Research Article
  • Citations4

Federated Data Quality Assessment Approach: Robust Learning With Mixed Label Noise.

  • Dec 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Bixiao Zeng +5
  • Research Article
  • Citations32

Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels

  • Feb 22, 2024
  • ACM Transactions on Intelligent Systems and Technology
  • Vasileios Tsouvalas +3
  • Research Article
  • Citations2

Enhanced Sample Selection with Confidence Tracking: Identifying Correctly Labeled Yet Hard-to-Learn Samples in Noisy Data

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Weiran Pan +3
  • Research Article
  • Citations2

FedGSCA: Medical Federated Learning With Global Sample Selector and Client Adaptive Adjuster Under Label Noise.

  • Aug 01, 2026
  • IEEE journal of biomedical and health informatics
  • Mengwen Ye +5
  • Research Article
  • Citations10

Regroup Median Loss for Combating Label Noise

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Fengpeng Li +3
  • Research Article
  • Citations68

Client Selection for Federated Learning With Label Noise

  • Feb 01, 2022
  • IEEE Transactions on Vehicular Technology
  • Miao Yang +4
  • Research Article
  • Citations2

Joint Client-and-Sample Selection for Federated Learning via Bi-Level Optimization

  • Dec 01, 2024
  • IEEE Transactions on Mobile Computing
  • Anran Li +6
  • Research Article
  • Citations28

CLC: A Consensus-based Label Correction Approach in Federated Learning

  • Jun 21, 2022
  • ACM Transactions on Intelligent Systems and Technology
  • Bixiao Zeng +4
  • Research Article
  • Citations6

Mitigating data imbalance and noise: A divergence-based approach with enhanced sample selection

  • Jul 26, 2024
  • Neurocomputing
  • Xuan Chen +5
  • Conference Article
  • Citations53

Adaptive Sample Selection for Robust Learning under Label Noise

  • Jan 01, 2023
  • Deep Patel +1
  • Research Article
  • Citations23

FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning

  • Mar 24, 2024
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Xinyuan Ji +6
  • Research Article
  • Citations11

FedCSS: Joint Client-and-Sample Selection for Hard Sample-Aware Noise-Robust Federated Learning

  • Nov 13, 2023
  • Proceedings of the ACM on Management of Data
  • Anran Li +5
  • Conference Article
  • Citations82

Convergence Time Minimization of Federated Learning over Wireless Networks

  • Jun 01, 2020
  • Mingzhe Chen +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.