CLDP-pFedAvg: Safeguarding Client Data Privacy in Personalized Federated Averaging
Open Access
- 20 November 2024
- journal article
- research article
- Published by MDPI AG in Mathematics
- Vol. 12 (22) , 3630
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.Keywords
This publication has 21 references indexed in Scilit:
- Federated Momentum Contrastive ClusteringACM Transactions on Intelligent Systems and Technology, 2024
- Federated Learning With Sparsified Model Perturbation: Improving Accuracy Under Client-Level Differential PrivacyIEEE Transactions on Mobile Computing, 2023
- Personalized Federated Learning With Differential Privacy and Convergence GuaranteeIEEE Transactions on Information Forensics and Security, 2023
- Differential Privacy for Deep and Federated Learning: A SurveyIEEE Access, 2022
- Privacy‐preserving federated learning based on multi‐key homomorphic encryptionInternational Journal of Intelligent Systems, 2022
- Federated learning on non-IID data: A surveyNeurocomputing, 2021
- A survey on federated learningKnowledge-Based Systems, 2021
- Federated Learning: Challenges, Methods, and Future DirectionsIEEE Signal Processing Magazine, 2020
- Personalized Federated Learning With Differential PrivacyIEEE Internet of Things Journal, 2020
- The Algorithmic Foundations of Differential PrivacyFoundations and Trends® in Theoretical Computer Science, 2014