# Federated Learning with Instance-Dependent Noisy Label

arXiv: https://arxiv.org/abs/2312.10324 · HTML: https://mlsanity.com/paper/2312.10324/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 19 references that are in the map.
- First posted on arXiv 16 Dec 2023.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies](https://mlsanity.com/paper/2010.01243/) (2020)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Learning to Learn from Noisy Labeled Data](https://mlsanity.com/paper/1812.05214/) (2018)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [FedCorr: Multi-Stage Federated Learning for Label Noise Correction](https://mlsanity.com/paper/2204.04677/) (2022)
- [Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation](https://mlsanity.com/paper/2206.02791/) (2022)
- [A Unified Analysis of Federated Learning with Arbitrary Client Participation](https://mlsanity.com/paper/2205.13648/) (2022)
- [Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2012.01700/) (2020)
- [Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network](https://mlsanity.com/paper/2105.13001/) (2021)

## Built on by (most cited first, 9 of 9)

- [LoRA-FAIR: Federated LoRA Fine-Tuning with Aggregation and Initialization Refinement](https://mlsanity.com/paper/2411.14961/) (2024)
- [Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains](https://mlsanity.com/paper/2403.09048/) (2024)
- [From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcare](https://mlsanity.com/paper/2409.09727/) (2024)
- [FedALT: Federated Fine-Tuning through Adaptive Local Training with Rest-of-World LoRA](https://mlsanity.com/paper/2503.11880/) (2025)
- [FedEL: Federated Elastic Learning for Heterogeneous Devices](https://mlsanity.com/paper/2509.16902/) (2025)
- [Enhancing Convergence in Federated Learning: A Contribution-Aware Asynchronous Approach](https://mlsanity.com/paper/2402.10991/) (2024)
- [Data Quality Control in Federated Instruction-tuning of Large Language Models](https://mlsanity.com/paper/2410.11540/) (2024)
- [Federated Markov Imputation: Privacy-Preserving Temporal Imputation in Multi-Centric ICU Environments](https://mlsanity.com/paper/2509.20867/) (2025)
- [Label Granularity Skew in Federated Learning with Hierarchical Image Classification](https://mlsanity.com/paper/2608.09236/) (2026)

## 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.