# Quantifying the Impact of Label Noise on Federated Learning

arXiv: https://arxiv.org/abs/2211.07816 · HTML: https://mlsanity.com/paper/2211.07816/

## 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 (most cited first, 30 of 34)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://mlsanity.com/paper/2007.07481/) (2020)
- [Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://mlsanity.com/paper/1909.06335/) (2019)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Fantastic Generalization Measures and Where to Find Them](https://mlsanity.com/paper/1912.02178/) (2019)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://mlsanity.com/paper/1907.09693/) (2019)
- [Federated Learning on Non-IID Data: A Survey](https://mlsanity.com/paper/2106.06843/) (2021)
- [A Field Guide to Federated Optimization](https://mlsanity.com/paper/2107.06917/) (2021)
- [Label Noise SGD Provably Prefers Flat Global Minimizers](https://mlsanity.com/paper/2106.06530/) (2021)
- [Path-SGD: Path-Normalized Optimization in Deep Neural Networks](https://mlsanity.com/paper/1506.02617/) (2015)
- [FedCorr: Multi-Stage Federated Learning for Label Noise Correction](https://mlsanity.com/paper/2204.04677/) (2022)
- [FedAvg with Fine Tuning: Local Updates Lead to Representation Learning](https://mlsanity.com/paper/2205.13692/) (2022)
- [Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2012.01700/) (2020)
- [On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics](https://mlsanity.com/paper/2007.15623/) (2020)
- [Cross-Silo Federated Learning: Challenges and Opportunities](https://mlsanity.com/paper/2206.12949/) (2022)
- [FOCUS: Dealing with Label Quality Disparity in Federated Learning](https://mlsanity.com/paper/2001.11359/) (2020)
- [Federated Learning under Distributed Concept Drift](https://mlsanity.com/paper/2206.00799/) (2022)
- [Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learning](https://mlsanity.com/paper/2005.02503/) (2020)
- [Generalized Data Weighting via Class-level Gradient Manipulation](https://mlsanity.com/paper/2111.00056/) (2021)
- [An Instance-Dependent Simulation Framework for Learning with Label Noise](https://mlsanity.com/paper/2107.11413/) (2021)
- [Federated Noisy Client Learning](https://mlsanity.com/paper/2106.13239/) (2021)
- [FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels](https://mlsanity.com/paper/2205.10110/) (2022)
- [Communication-Efficient Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2206.05558/) (2022)
- [Capacity Control of ReLU Neural Networks by Basis-path Norm](https://mlsanity.com/paper/1809.07122/) (2018)
- [Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies](https://mlsanity.com/paper/2109.03999/) (2021)

## Built on by (most cited first, 3 of 3)

- [FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering](https://mlsanity.com/paper/2301.12379/) (2023)
- [Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies](https://mlsanity.com/paper/2310.05397/) (2023)
- [Price of Stability in Quality-Aware Federated Learning](https://mlsanity.com/paper/2310.08790/) (2023)

## 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.