Abstract
The personalized federated averaging algorithm integrates a federated averaging approach with a model-agnostic meta-learning technique. In real-world heterogeneous scenarios, it is essential to implement additional privacy protection techniques for personalized federated learning. We propose a novel differentially private federated meta-learning scheme, CLDP-pFedAvg, which achieves client-level differential privacy guarantees for federated learning involving large heterogeneous clients. The client-level differentially private meta-based FedAvg algorithm enables clients to upload local model parameters for aggregation securely. Furthermore, we provide a convergence analysis of the clipping-enabled differentially private meta-based FedAvg algorithm. The proposed strategy is evaluated across various datasets, and the findings indicate that our approach offers improved privacy protection while maintaining model accuracy.

This publication has 21 references indexed in Scilit: