Voting-based Approaches For Differentially Private Federated Learning
Not on the map. Why?
Abstract (arXiv)
Differentially Private Federated Learning (DPFL) is an emerging field with many applications. Gradient averaging based DPFL methods require costly communication rounds and hardly work with large-capacity models, due to the explicit dimension dependence in its added noise. In this work, inspired by knowledge transfer non-federated privacy learning from Papernot et al.(2017; 2018), we design two new DPFL schemes, by voting among the data labels returned from each local model, instead of averaging the gradients, which avoids the dimension dependence and significantly reduces the communication cost. Theoretically, by applying secure multi-party computation, we could exponentially amplify the (data-dependent) privacy guarantees when the margin of the voting scores are large. Extensive experiments show that our approaches significantly improve the privacy-utility trade-off over the state-of-the-arts in DPFL.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Oct 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 4; 2023: 4; 2024: 2; 2025: 2; 2026: 1.
14 papers.
Sort:
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
- 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 35
- 2023Make Landscape Flatter in Differentially Private Federated Learningcited by 33
- 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
- 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
- 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
- 2021Constrained Differentially Private Federated Learning for Low-bandwidth Devicescited by 6
- 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
- 2023Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacycited by 5
- 2024Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilitiescited by 3
- 2024DP2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimizationcited by 0
- 2025Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updatescited by 0
- 2026Tackling Privacy Heterogeneity in Differentially Private Federated Learning26 Feb 2026
- 2025DP-Hype: Federated Differentially Private Hyperparameter Search6 Oct 2025
- 2025Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates12 Mar 2025
- 2024DP2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization20 Sep 2024
- 2024Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilities16 Sep 2024
- 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency20 Jul 2023
- 2023Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy1 May 2023
- 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacy15 Apr 2023
- 2023Make Landscape Flatter in Differentially Private Federated Learning20 Mar 2023
- 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks8 Sep 2022
- 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning9 Jun 2022
- 2022Differentially Private Federated Learning with Local Regularization and Sparsification7 Mar 2022
- 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
- 2022Differentially Private Federated Learning with Local Regularization and Sparsificationcited by 35
- 2023Make Landscape Flatter in Differentially Private Federated Learningcited by 33
- 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learningcited by 27
- 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiencycited by 21
- 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attackscited by 12
- 2021Constrained Differentially Private Federated Learning for Low-bandwidth Devicescited by 6
- 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacycited by 5
- 2023Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacycited by 5
- 2024Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilitiescited by 3
- 2024DP2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimizationcited by 0
- 2025Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updatescited by 0
12 most cited of 14 All 14 (JSON)
- 2026Tackling Privacy Heterogeneity in Differentially Private Federated Learning26 Feb 2026
- 2025DP-Hype: Federated Differentially Private Hyperparameter Search6 Oct 2025
- 2025Differential Privacy Personalized Federated Learning Based on Dynamically Sparsified Client Updates12 Mar 2025
- 2024DP2-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization20 Sep 2024
- 2024Federated Learning for Smart Grid: A Survey on Applications and Potential Vulnerabilities16 Sep 2024
- 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency20 Jul 2023
- 2023Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy1 May 2023
- 2023Communication and Energy Efficient Wireless Federated Learning with Intrinsic Privacy15 Apr 2023
- 2023Make Landscape Flatter in Differentially Private Federated Learning20 Mar 2023
- 2022Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks8 Sep 2022
- 2022A Critical Review on the Use (and Misuse) of Differential Privacy in Machine Learning9 Jun 2022
- 2022Differentially Private Federated Learning with Local Regularization and Sparsification7 Mar 2022
12 newest of 14 All 14 (JSON)