Labeling Chaos to Learning Harmony: Federated Learning with Noisy Labels

Federated Learning (FL) is a distributed machine learning paradigm that enables learning models from decentralized private datasets, where the labeling effort is entrusted to the clients. While most existing FL approaches assume high-quality labels are readily available on users' devices; in re...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-05
Hauptverfasser:	Tsouvalas, Vasileios, Aaqib Saeed, Tanir Ozcelebi, Meratnia, Nirvana
Format:	Artikel
Sprache:	eng
Schlagworte:	Clients Data exchange Datasets Federated learning Labels Machine learning Noise levels Servers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!