# FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels

arXiv: https://arxiv.org/abs/2205.10110 · HTML: https://mlsanity.com/paper/2205.10110/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 45 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 30 of 38)

- [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)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Personalized Federated Learning with Moreau Envelopes](https://mlsanity.com/paper/2006.08848/) (2020)
- [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://mlsanity.com/paper/1610.02527/) (2016)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [Exploiting Shared Representations for Personalized Federated Learning](https://mlsanity.com/paper/2102.07078/) (2021)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Federated Machine Learning: Concept and Applications](https://mlsanity.com/paper/1902.04885/) (2019)
- [Adaptive Personalized Federated Learning](https://mlsanity.com/paper/2003.13461/) (2020)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [SELF: Learning to Filter Noisy Labels with Self-Ensembling](https://mlsanity.com/paper/1910.01842/) (2019)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)

## Built on by (most cited first, 12 of 12)

- [Federated Learning from Pre-Trained Models: A Contrastive Learning Approach](https://mlsanity.com/paper/2209.10083/) (2022)
- [Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data](https://mlsanity.com/paper/2301.09152/) (2023)
- [FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity](https://mlsanity.com/paper/2305.05230/) (2023)
- [FedNoisy: Federated Noisy Label Learning Benchmark](https://mlsanity.com/paper/2306.11650/) (2023)
- [MSA-GCN:Multiscale Adaptive Graph Convolution Network for Gait Emotion Recognition](https://mlsanity.com/paper/2209.08988/) (2022)
- [FNBench: Benchmarking Robust Federated Learning against Noisy Labels](https://mlsanity.com/paper/2505.06684/) (2025)
- [Quantifying the Impact of Label Noise on Federated Learning](https://mlsanity.com/paper/2211.07816/) (2022)
- [Keep It Simple: Fault Tolerance Evaluation of Federated Learning with Unreliable Clients](https://mlsanity.com/paper/2305.09856/) (2023)
- [Data Quality Control in Federated Instruction-tuning of Large Language Models](https://mlsanity.com/paper/2410.11540/) (2024)
- [Learning Locally, Revising Globally: Global Reviser for Federated Learning with Noisy Labels](https://mlsanity.com/paper/2412.00452/) (2024)
- [Federated Learning and Class Imbalances](https://mlsanity.com/paper/2601.06348/) (2026)
- [SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels](https://mlsanity.com/paper/2605.11060/) (2026)

## Abstract (arXiv)

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. Hence, the labels in practice are usually annotated by clients of varying expertise or criteria and thus contain different amounts of noises. Local training on noisy labels can easily result in overfitting to noisy labels, which is devastating to the global model through aggregation. Although recent robust FL methods take malicious clients into account, they have not addressed local noisy labels on each device and the impact to the global model. In this paper, we develop a simple two-level sampling method "FedNoiL" that (1) selects clients for more robust global aggregation on the server; and (2) selects clean labels and correct pseudo-labels at the client end for more robust local training. The sampling probabilities are built upon clean label detection by the global model. Moreover, we investigate different schedules changing the local epochs between aggregations over the course of FL, which notably improves the communication and computation efficiency in noisy label setting. In experiments with homogeneous/heterogeneous data distributions and noise ratios, we observed that direct combinations of SOTA FL methods with SOTA noisy-label learning methods can easily fail but our method consistently achieves better and robust performance.