mlsanityData to 14 Oct 2026

Quantifying the Impact of Label Noise on Federated Learning

arXiv 2211.07816 ↗First posted 15 Nov 2022cs.LG stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) is a distributed machine learning paradigm where clients collaboratively train a model using their local (human-generated) datasets. While existing studies focus on FL algorithm development to tackle data heterogeneity across clients, the important issue of data quality (e.g., label noise) in FL is overlooked. This paper aims to fill this gap by providing a quantitative study on the impact of label noise on FL. We derive an upper bound for the generalization error that is linear in the clients' label noise level. Then we conduct experiments on MNIST and CIFAR-10 datasets using various FL algorithms. Our empirical results show that the global model accuracy linearly decreases as the noise level increases, which is consistent with our theoretical analysis. We further find that label noise slows down the convergence of FL training, and the global model tends to overfit when the noise level is high.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 34 of its 61 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

34 of 61 references.

References · 34

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  5. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  6. 2017Exploring Generalization in Deep Learningcited by 600
  7. 2019Fantastic Generalization Measures and Where to Find Themcited by 513
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  9. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 413
  10. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 395
  11. 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 374
  12. 2021Federated Learning on Non-IID Data: A Surveycited by 346
22 more
  1. 2021A Field Guide to Federated Optimizationcited by 315
  2. 2021Label Noise SGD Provably Prefers Flat Global Minimizerscited by 121
  3. 2015Path-SGD: Path-Normalized Optimization in Deep Neural Networkscited by 120
  4. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  5. 2022FedAvg with Fine Tuning: Local Updates Lead to Representation Learningcited by 56
  6. 2020Robust Federated Learning with Noisy Labelscited by 40
  7. 2020On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamicscited by 39
  8. 2022Cross-Silo Federated Learning: Challenges and Opportunitiescited by 38
  9. 2020FOCUS: Dealing with Label Quality Disparity in Federated Learningcited by 36
  10. 2022Federated Learning under Distributed Concept Driftcited by 36
  11. 2020Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learningcited by 21
  12. 2021Generalized Data Weighting via Class-level Gradient Manipulationcited by 15
  13. 2021An Instance-Dependent Simulation Framework for Learning with Label Noisecited by 14
  14. 2021Federated Noisy Client Learningcited by 13
  15. 2022FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labelscited by 12
  16. 2022Communication-Efficient Robust Federated Learning with Noisy Labelscited by 11
  17. 2018Capacity Control of ReLU Neural Networks by Basis-path Normcited by 10
  18. 2021Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategiescited by 9
  19. 2021Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentationcited by 4
  20. 2022Federated Learning with Noisy User Feedbackcited by 4
  21. 2022Decentralized Stochastic Variance Reduced Extragradient Methodcited by 3
  22. 2022Incentivizing Data Contribution in Cross-Silo Federated Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 3.

3 papers.

  1. 2023FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clusteringcited by 15
  2. 2023Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologiescited by 3
  3. 2023Price of Stability in Quality-Aware Federated Learningcited by 0