# Learning Cautiously in Federated Learning with Noisy and Heterogeneous Clients

arXiv: https://arxiv.org/abs/2304.02892 · HTML: https://mlsanity.com/paper/2304.02892/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 6 Apr 2023.

## Builds on (most cited first, 14 of 14)

- [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)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [FedProto: Federated Prototype Learning across Heterogeneous Clients](https://mlsanity.com/paper/2105.00243/) (2021)
- [FedCorr: Multi-Stage Federated Learning for Label Noise Correction](https://mlsanity.com/paper/2204.04677/) (2022)
- [Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2012.01700/) (2020)
- [FOCUS: Dealing with Label Quality Disparity in Federated Learning](https://mlsanity.com/paper/2001.11359/) (2020)
- [FEDIC: Federated Learning on Non-IID and Long-Tailed Data via Calibrated Distillation](https://mlsanity.com/paper/2205.00172/) (2022)

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

- [Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition](https://mlsanity.com/paper/2406.19931/) (2024)
- [Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data](https://mlsanity.com/paper/2405.06413/) (2024)
- [FNBench: Benchmarking Robust Federated Learning against Noisy Labels](https://mlsanity.com/paper/2505.06684/) (2025)
- [FediOS: Decoupling Orthogonal Subspaces for Personalization in Feature-skew Federated Learning](https://mlsanity.com/paper/2311.18559/) (2023)
- [FedMLP: Federated Multi-Label Medical Image Classification under Task Heterogeneity](https://mlsanity.com/paper/2406.18995/) (2024)
- [Data Quality Control in Federated Instruction-tuning of Large Language Models](https://mlsanity.com/paper/2410.11540/) (2024)
- [FedGuCci: Making Local Models More Connected in Landscape for Federated Learning](https://mlsanity.com/paper/2402.18949/) (2024)
- [FedStyle: Style-Based Federated Learning Crowdsourcing Framework for Art Commissions](https://mlsanity.com/paper/2404.16336/) (2024)
- [FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning](https://mlsanity.com/paper/2407.05098/) (2024)
- [Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data](https://mlsanity.com/paper/2505.09733/) (2025)
- [FedCova: Robust Federated Covariance Learning Against Noisy Labels](https://mlsanity.com/paper/2603.04062/) (2026)
- [FedRG: Unleashing the Representation Geometry for Federated Learning with Noisy Clients](https://mlsanity.com/paper/2603.19722/) (2026)

## Abstract (arXiv)

Federated learning (FL) is a distributed framework for collaboratively training with privacy guarantees. In real-world scenarios, clients may have Non-IID data (local class imbalance) with poor annotation quality (label noise). The co-existence of label noise and class imbalance in FL's small local datasets renders conventional FL methods and noisy-label learning methods both ineffective. To address the challenges, we propose FedCNI without using an additional clean proxy dataset. It includes a noise-resilient local solver and a robust global aggregator. For the local solver, we design a more robust prototypical noise detector to distinguish noisy samples. Further to reduce the negative impact brought by the noisy samples, we devise a curriculum pseudo labeling method and a denoise Mixup training strategy. For the global aggregator, we propose a switching re-weighted aggregation method tailored to different learning periods. Extensive experiments demonstrate our method can substantially outperform state-of-the-art solutions in mix-heterogeneous FL environments.