mlsanityData to 14 Oct 2026

Privacy-preserving Federated Primal-dual Learning for Non-convex and Non-smooth Problems with Model Sparsification

arXiv 2310.19558 ↗First posted 30 Oct 2023cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has been recognized as a rapidly growing research area, where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients' data. This paper delves into a class of federated problems characterized by non-convex and non-smooth loss functions, that are prevalent in FL applications but challenging to handle due to their intricate non-convexity and non-smoothness nature and the conflicting requirements on communication efficiency and privacy protection. In this paper, we propose a novel federated primal-dual algorithm with bidirectional model sparsification tailored for non-convex and non-smooth FL problems, and differential privacy is applied for privacy guarantee. Its unique insightful properties and some privacy and convergence analyses are also presented as the FL algorithm design guidelines. Extensive experiments on real-world data are conducted to demonstrate the effectiveness of the proposed algorithm and much superior performance than some state-of-the-art FL algorithms, together with the validation of all the analytical results and properties.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 43 of its 64 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

43 of 64 references.

References · 43

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  7. 2018How To Backdoor Federated Learningcited by 765
  8. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  9. 2021Federated Learning Based on Dynamic Regularizationcited by 562
  10. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  11. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  12. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
31 more
  1. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  2. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  3. 2018Privacy Amplification by Subsampling: Tight Analyses via Couplings and Divergencescited by 242
  4. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
  5. 2018cpSGD: Communication-efficient and differentially-private distributed SGDcited by 158
  6. 2018Federated Meta-Learning with Fast Convergence and Efficient Communicationcited by 155
  7. 2020FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Datacited by 144
  8. 2018ATOMO: Communication-efficient Learning via Atomic Sparsificationcited by 136
  9. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 132
  10. 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
  11. 2019Variance Reduced Local SGD with Lower Communication Complexitycited by 80
  12. 2021Differentially Private Federated Learning on Heterogeneous Datacited by 74
  13. 2014Convergence Analysis of Alternating Direction Method of Multipliers for a Family of Nonconvex Problemscited by 64
  14. 2020Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Frameworkcited by 59
  15. 2020Federated Learning With Quantized Global Model Updatescited by 55
  16. 2018Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communicationcited by 51
  17. 2019Collecting and Analyzing Multidimensional Data with Local Differential Privacycited by 49
  18. 2020Federated Composite Optimizationcited by 49
  19. 2022Federated Learning via Inexact ADMMcited by 44
  20. 2018DP-ADMM: ADMM-based Distributed Learning with Differential Privacycited by 42
  21. 2021Quantized Federated Learning under Transmission Delay and Outage Constraintscited by 37
  22. 2022Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacycited by 33
  23. 2021FedDR -- Randomized Douglas-Rachford Splitting Algorithms for Nonconvex Federated Composite Optimizationcited by 29
  24. 2023Why Batch Normalization Damage Federated Learning on Non-IID Data?cited by 29
  25. 2020Private and Communication-Efficient Edge Learning: A Sparse Differential Gaussian-Masking Distributed SGD Approachcited by 18
  26. 2020Compression Boosts Differentially Private Federated Learningcited by 13
  27. 2022Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Frameworkcited by 9
  28. 2023Differentially Private Federated Clustering over Non-IID Datacited by 7
  29. 2015Stochastic Proximal Gradient Consensus Over Random Networkscited by 5
  30. 2016NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimizationcited by 5
  31. 2022Federated Stochastic Primal-dual Learning with Differential Privacycited by 5

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024A Multivocal Literature Review on Privacy and Fairness in Federated Learningcited by 0
  2. 2025Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participationcited by 0