Optimizing the Numbers of Queries and Replies in Federated Learning with Differential Privacy

Abstract

Federated learning (FL) empowers distributed clients to collaboratively train a shared machine learning model through exchanging parameter information. Despite the fact that FL can protect clients' raw data, malicious users can still crack original data with disclosed parameters. To amend this flaw, differential privacy (DP) is incorporated into FL clients to disturb original parameters, which however can significantly impair the accuracy of the trained model. In this work, we study a crucial question which has been vastly overlooked by existing works: what are the optimal numbers of queries and replies in FL with DP so that the final model accuracy is maximized. In FL, the parameter server (PS) needs to query participating clients for multiple global iterations to complete training. Each client responds a query from the PS by conducting a local iteration. Our work investigates how many times the PS should query clients and how many times each client should reply the PS. We investigate two most extensively used DP mechanisms (i.e., the Laplace mechanism and Gaussian mechanisms). Through conducting convergence rate analysis, we can determine the optimal numbers of queries and replies in FL with DP so that the final model accuracy can be maximized. Finally, extensive experiments are conducted with publicly available datasets: MNIST and FEMNIST, to verify our analysis and the results demonstrate that properly setting the numbers of queries and replies can significantly improve the final model accuracy in FL with DP.

References in corpus (13)

• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
• Differentially Private Federated Learning: A Client Level Perspective
• iDLG: Improved Deep Leakage from Gradients
• LEAF: A Benchmark for Federated Settings
• Protection Against Reconstruction and Its Applications in Private Federated Learning
• Threats to Federated Learning: A Survey
• Federated Learning with Bayesian Differential Privacy
• Differential Privacy-enabled Federated Learning for Sensitive Health Data
• A Framework for Evaluating Gradient Leakage Attacks in Federated Learning
• Improved asynchronous parallel optimization analysis for stochastic incremental methods
• Differentially-Private "Draw and Discard" Machine Learning