A Theoretical Analysis of Efficiency Constrained Utility-Privacy Bi-Objective Optimization in Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated learning (FL) enables multiple clients to collaboratively learn a shared model without sharing their individual data. Concerns about utility, privacy, and training efficiency in FL have garnered significant research attention. Differential privacy has emerged as a prevalent technique in FL, safeguarding the privacy of individual user data while impacting utility and training efficiency. Within Differential Privacy Federated Learning (DPFL), previous studies have primarily focused on the utility-privacy trade-off, neglecting training efficiency, which is crucial for timely completion. Moreover, differential privacy achieves privacy by introducing controlled randomness (noise) on selected clients in each communication round. Previous work has mainly examined the impact of noise level (σ) and communication rounds (T) on the privacy-utility dynamic, overlooking other influential factors like the sample ratio (q, the proportion of selected clients). This paper systematically formulates an efficiency-constrained utility-privacy bi-objective optimization problem in DPFL, focusing on σ, T, and q. We provide a comprehensive theoretical analysis, yielding analytical solutions for the Pareto front. Extensive empirical experiments verify the validity and efficacy of our analysis, offering valuable guidance for low-cost parameter design in DPFL.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 27 Dec 2023.
Builds on
28 of 58 references.
References · 28
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2016Deep Learning with Differential Privacycited by 2,682
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2019Deep Leakage from Gradientscited by 1,004
- 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
- 2020An Efficient Framework for Clustered Federated Learningcited by 505
- 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
- 2020iDLG: Improved Deep Leakage from Gradientscited by 367
- 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
16 more
- 2018Distributed learning of deep neural network over multiple agentscited by 277
- 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 196
- 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
- 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
- 2019Deep Learning with Gaussian Differential Privacycited by 112
- 2021Multi-Objective Bayesian Optimization over High-Dimensional Search Spacescited by 87
- 2019Detailed comparison of communication efficiency of split learning and federated learningcited by 76
- 2021Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacycited by 66
- 2022Pareto Set Learning for Expensive Multi-Objective Optimizationcited by 51
- 2020Wireless Federated Learning with Local Differential Privacycited by 50
- 2019The stochastic multi-gradient algorithm for multi-objective optimization and its application to supervised machine learningcited by 45
- 2022No Free Lunch Theorem for Security and Utility in Federated Learningcited by 39
- 2022On Convergence of FedProx: Local Dissimilarity Invariant Bounds, Non-smoothness and Beyondcited by 37
- 2021The Role of Adaptive Optimizers for Honest Private Hyperparameter Selectioncited by 25
- 2023Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learningcited by 12
- 2020A Theoretical Perspective on Differentially Private Federated Multi-task Learningcited by 8
Built on by
Citing papers per year: 2024: 1.
1 paper.