Can I read FednnP Federated Unlearning With Multiple Client Set Partitions on EtoBox?

FednnP Federated Unlearning With Multiple Client Set Partitions by bagri.asmaa is a document available to read on EtoBox.

What is FednnP Federated Unlearning With Multiple Client Set Partitions about?

The paper introduces FednP, a federated unlearning algorithm that addresses the challenges of removing specific training data from models in federated learning (FL) environments. By partitioning client sets into multiple subsets, FednP enhances prediction accuracy while controlling retraining costs and efficiently managing unlearning requests. Extensive experiments demonstrate that FednP improves model performance compared to existing methods while adhering to privacy regulations.

Author

bagri.asmaa

Language

EN