Dap-FL: Federated Learning Flourishes by Adaptive Tuning and Secure Aggregation

Federated learning (FL), an attractive and promising distributed machine learning paradigm, has sparked extensive interest in exploiting tremendous data stored on ubiquitous mobile devices. However, conventional FL suffers severely from resource heterogeneity, as clients with weak computational and...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on parallel and distributed systems 2023-06, Vol.34 (6), p.1-18
Hauptverfasser:	Chen, Qian, Wang, Zilong, Chen, Jiawei, Yan, Haonan, Lin, Xiaodong
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation models Adaptive systems Adaptive training Clients Computational modeling Data models deep deterministic policy gradient deep reinforcement learning Electronic devices Federated learning Heterogeneity Machine learning Mathematical models Model accuracy Parameters Predictive models Privacy privacy preservation Security Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!