A Communication-Efficient, Privacy-Preserving Federated Learning Algorithm Based on Two-Stage Gradient Pruning and Differentiated Differential Privacy

There are several unsolved problems in federated learning, such as the security concerns and communication costs associated with it. Differential privacy (DP) offers effective privacy protection by introducing noise to parameters based on rigorous privacy definitions. However, excessive noise additi...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Yong Li, Wei Du, Liquan Han, Zhenjian Zhang, Tongtong Liu
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	MDPI AG 2023-11-01
Cyfres:	Sensors
Pynciau:	differentiated differential privacy federated learning gradient pruning privacy preserving
Mynediad Ar-lein:	https://www.mdpi.com/1424-8220/23/23/9305
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!