Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
Not on the map. Why?
Abstract (arXiv)
This paper tackles the challenge of achieving Differential Privacy (DP) in Federated Learning (FL) under partial-participation, where only a subset of the machines participate in each time-step. While previous work achieved optimal performance in full-participation settings, these methods struggled to extend to partial-participation scenarios. Our approach fills this gap by introducing a novel noise-cancellation mechanism that preserves privacy without sacrificing convergence rates or computational efficiency. We analyze our method within the Stochastic Convex Optimization (SCO) framework and show that it delivers optimal performance for both homogeneous and heterogeneous data distributions. This work expands the applicability of DP in FL, offering an efficient and practical solution for privacy-preserving learning in distributed systems with partial participation.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 3 Jun 2025.
Builds on
24 of 41 references.
References · 24
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2016Deep Learning with Differential Privacycited by 2,728
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
- 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
- 2019Momentum-Based Variance Reduction in Non-Convex SGDcited by 306
- 2019Private Stochastic Convex Optimization with Optimal Ratescited by 186
- 2021Practical and Private (Deep) Learning without Sampling or Shufflingcited by 170
- 2020Private Stochastic Convex Optimization: Optimal Rates in Linear Timecited by 153
- 2018Differentially Private Empirical Risk Minimization Revisited: Faster and More Generalcited by 128
- 2014Differentially Private Empirical Risk Minimization: Efficient Algorithms and Tight Error Boundscited by 107
- 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
- 2019UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimizationcited by 56
12 more
- 2018DP-ADMM: ADMM-based Distributed Learning with Differential Privacycited by 42
- 2021Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Lossescited by 30
- 2021Differentially private inference via noisy optimizationcited by 27
- 2022Private Non-Convex Federated Learning Without a Trusted Servercited by 26
- 2023Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacycited by 18
- 2014Private Multiplicative Weights Beyond Linear Queriescited by 17
- 2021Shuffle Private Stochastic Convex Optimizationcited by 17
- 2023Faster Differentially Private Convex Optimization via Second-Order Methodscited by 13
- 2024Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Lossescited by 8
- 2023μ2-SGD: Stable Stochastic Optimization via a Double Momentum Mechanismcited by 4
- 2024Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systemscited by 3
- 2021DPNCT: A Differential Private Noise Cancellation Scheme for Load Monitoring and Billing for Smart Meterscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.