VCFedAdam: A Verifiable and Compressed FedAdam Aggregation Scheme for Federated Learning in Distributed Sensor Networks
Experimental results show that VCFedAdam reduces computation overhead by 90.25% and communication overhead by 75.38% compared with traditional secure aggregation, and security analysis confirms that VCFedAdam achieves both privacy protection and aggregation verifiability.
Zhi-Wei Si, Xiu-Heng Liao, Ziang Wu et al.
· Italian National Conference... · 0 citations