mlsanityData to 7 Oct 2026

Federated Learning with Instance-Dependent Noisy Label

arXiv 2312.10324 ↗First posted 16 Dec 2023cs.LG cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) with noisy labels poses a significant challenge. Existing methods designed for handling noisy labels in centralized learning tend to lose their effectiveness in the FL setting, mainly due to the small dataset size and the heterogeneity of client data. While some attempts have been made to tackle FL with noisy labels, they primarily focused on scenarios involving class-conditional noise. In this paper, we study the more challenging and practical issue of instance-dependent noise (IDN) in FL. We introduce a novel algorithm called FedBeat (Federated Learning with Bayesian Ensemble-Assisted Transition Matrix Estimation). FedBeat aims to build a global statistically consistent classifier using the IDN transition matrix (IDNTM), which encompasses three synergistic steps: (1) A federated data extraction step that constructs a weak global model and extracts high-confidence data using a Bayesian model ensemble method. (2) A federated transition matrix estimation step in which clients collaboratively train an IDNTM estimation network based on the extracted data. (3) A federated classifier correction step that enhances the global model's performance by training it using a loss function tailored for noisy labels, leveraging the IDNTM. Experiments conducted on CIFAR-10 and SVHN verify that the proposed method significantly outperforms state-of-the-art methods.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 15 of its 19 references that are in the map. First posted on arXiv 16 Dec 2023.

Builds on

15 of 19 references.

References · 15

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2018Federated Learning with Non-IID Datacited by 1,099
  5. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 415
  6. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  7. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
  8. 2020FedBE: Making Bayesian Model Ensemble Applicable to Federated Learningcited by 176
  9. 2018Learning to Learn from Noisy Labeled Datacited by 160
  10. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  11. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  12. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
3 more
  1. 2022A Unified Analysis of Federated Learning with Arbitrary Client Participationcited by 45
  2. 2020Robust Federated Learning with Noisy Labelscited by 40
  3. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 3; 2026: 1.

9 papers.

  1. 2024LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinementcited by 37
  2. 2024Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domainscited by 27
  3. 2024From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcarecited by 16
  4. 2025FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRAcited by 13
  5. 2025FedEL: Federated Elastic Learning for Heterogeneous Devicescited by 3
  6. 2024Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approachcited by 1
  7. 2024Data Quality Control in Federated Instruction-tuning of Large Language Modelscited by 1
  8. 2025Federated Markov Imputation: Privacy-Preserving Temporal Imputation in Multi-Centric ICU Environmentscited by 0
  9. 2026Label Granularity Skew in Federated Learning with Hierarchical Image Classificationcited by 0