English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Federated Learning (FL) is a distributed machine learning paradigm whereclients collaboratively train a model using their local (human-generated)datasets. While existing studies focus on FL algorithm development to tackledata 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 providinga quantitative study on the impact of label noise on FL. We derive an upperbound for the generalization error that is linear in the clients' label noiselevel. Then we conduct experiments on MNIST and CIFAR-10 datasets using variousFL algorithms. Our empirical results show that the global model accuracylinearly decreases as the noise level increases, which is consistent with ourtheoretical analysis. We further find that label noise slows down theconvergence of FL training, and the global model tends to overfit when thenoise level is high.

Quantifying the Impact of Label Noise on Federated Learning