With the widespread application of federated learning (FL) in data security scenarios, striking a balance between communication efficiency, system robustness, and data privacy has become a key challenge. Existing FL frameworks typically rely on a central server, which introduces single points of failure and potential privacy risks. Although communication compression can improve convergence efficiency, its application in decentralized scenarios remains limited, and it lacks rigorous privacy protection mechanisms. This paper proposes a new decentralized federated learning algorithm framework, DeFL-VP, which integrates communication compression, client-side variance reduction, and differential privacy (DP) mechanisms within a graph-structured network. Specifically, we introduce local control variables into the underlying architecture of decentralized federated learning to reduce gradient variance among clients, while designing a differential privacy algorithm based on a random response mechanism to protect user privacy. Theoretically, we prove the convergence of the proposed algorithm under non-convex smoothness conditions and provide an upper bound on the impact of privacy noise on the convergence rate. Experimental results under a decentralized non-IID setting show that DeFL-VP achieves stable convergence performance, maintains model utility, and obtains a lower attack AUC under membership inference attacks compared with the baseline methods.
- Open Access
- Article
DeFL-VP: Decentralized Federated Learning with Variance Reduction and Differential Privacy
- Ruihong Xiu 1,
- Rui Liu 1,*,
- Weixu Zhang 1,
- Xiaokai Liao 2,
- Kouichi Sakurai 3
Author Information
Received: 24 Apr 2026 | Revised: 16 Jun 2026 | Accepted: 24 Jun 2026 | Published: 25 Jun 2026
Abstract
References
- 1.
Hallaji, E.; Razavi-Far, R.; Saif, M.; et al. Decentralized federated learning: A survey on security and privacy. IEEE Trans. Big Data 2024, 10, 194–213.
- 2.
Zhang, Z.; Hu, R. Byzantine-robust federated learning with variance reduction and differential privacy. In Proceedings of the 2023 IEEE Conference on Communications and Network Security (CNS), Orlando, FL, USA, 2–5 October 2023; pp. 1–9.
- 3.
Fu, J.; Hong, Y.; Ling, X.; et al. Differentially private federated learning: A systematic review. ACM Comput. Surv. 2026, 58, 271.
- 4.
Zhang, C.; Weng, J.; Weng, J.; et al. Robust and secure federated learning with verifiable differential privacy. IEEE Trans. Dependable Secur. Comput. 2025, 22, 5713–5729.
- 5.
Mashiko, S.; Kawamata, Y.; Nakayama, T.; et al. Anomaly detection in double-entry bookkeeping data by federated learning system with non-model sharing approach. Sci. Rep. 2025, 15, 42208.
- 6.
Kanamori, S.; Abe, T.; Ito, T.; et al. Privacy-preserving federated learning for detecting fraudulent financial transactions in japanese banks. J. Inf. Process. 2022, 30, 789–795.
- 7.
Fukami, T.; Murata, T.; Niwa, K.; et al. Dp-norm: Differential privacy primal-dual algorithm for decentralized federated learning. IEEE Trans. Inf. Forensics Secur. 2024, 19, 5783–5797.
- 8.
Chen, S.; Yu, D.; Zou, Y.; et al. Decentralized wireless federated learning with differential privacy. IEEE Trans. Ind. Inform. 2022, 18, 6273–6282.
- 9.
Yan, Z.; Wicaksana, J.; Wang, Z.; et al. Variation-aware federated learning with multi-source decentralized medical image data. IEEE J. Biomed. Health Inform. 2020, 25, 2615–2628.
- 10.
Lu, Y.; Yu, Z.; Suri, N. Privacy-preserving decentralized federated learning over time-varying communication graph. ACM Trans. Priv. Secur. 2023, 26, 33.
- 11.
Sun, T.; Li, D.; Wang, B. Decentralized federated averaging. IEEE Trans. Pattern Anal. Mach. Intell. 2022, 45, 4289–4301.
- 12.
Xin, R.; Kar, S.; Khan, U.A. Decentralized stochastic optimization and machine learning: A unified variance-reduction framework for robust performance and fast convergence. IEEE Signal Process. Mag. 2020, 37, 102–113.
- 13.
Zhang, A.; Zhao, P.; Lu, W.; et al. Personalized Decentralized Federated Learning: A Privacy-Enhanced and Byzantine-Resilient Approach. IEEE Trans. Comput. Soc. Syst. 2025, 12, 3206–3217.
- 14.
Wu, J.; Li, C.; Wu, W.; et al. Client Selection in Federated Learning With Differential Privacy-Based Data Stream. IEEE Trans. Netw. 2025, 34, 1128–1144.
- 15.
Li, Q.; Wen, Z.; Wu, Z.; et al. A survey on federated learning systems: Vision, hype and reality for data privacy and protection. IEEE Trans. Knowl. Data Eng. 2023, 35, 3347–3366.
- 16.
Truex, S.; Baracaldo, N.; Anwar, A.; et al. A hybrid approach to privacy-preserving federated learning. In Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, London, UK, 15 November 2019; pp. 1–11.
- 17.
Wei, K.; Li, J.; Ding, M.; et al. Federated learning with differential privacy: Algorithms and performance analysis. IEEE Trans. Inf. Forensics Secur. 2020, 15, 3454–3469.
- 18.
Zhao, Y.; Zhao, J.; Yang, M.; et al. Local differential privacy-based federated learning for internet of things. IEEE Internet Things J. 2020, 8, 8836–8853.
- 19.
Chen, J.; Yan, H.; Liu, Z.; et al. When federated learning meets privacy-preserving computation. ACM Comput. Surv. 2024, 56, 319.
- 20.
Hidayat, M.A.; Nakamura, Y.; Arakawa, Y. Privacy-preserving federated learning with resource-adaptive compression for edge devices. IEEE Internet Things J. 2023, 11, 13180–13198.
- 21.
Dinh, C.T.; Tran, N.H.; Nguyen, T.D.; et al. Federated learning with proximal stochastic variance reduced gradient algorithms. In Proceedings of the 49th International Conference on Parallel Processing, Edmonton, AB, Canada, 17–20 August 2020; pp. 1–11.
- 22.
Zhang, H.; Li, C.; Dai, W.; et al. Federated learning based on model discrepancy and variance reduction. IEEE Trans. Neural Netw. Learn. Syst. 2025, 36, 10407–10421.
- 23.
Wang, B.; Fang, J.; Li, H.; et al. Communication-efficient federated learning: A variance-reduced stochastic approach with adaptive sparsification. IEEE Trans. Signal Process. 2023, 71, 3562–3576.
- 24.
Guo, Z.; Yu, K.; Lv, Z.; et al. Deep federated learning enhanced secure POI microservices for cyber-physical systems. IEEE Wirel. Commun. 2022, 29, 22–29.
- 25.
Taya, A.; Nishio, T.; Morikura, M.; et al. Decentralized and model-free federated learning: Consensus-based distillation in function space. IEEE Trans. Signal Inf. Process. Over Netw. 2022, 8, 799–814.
- 26.
Yue, G.; Yan, L.; Kang, L.; et al. Adapldp-fl: An adaptive local differential privacy for federated learning. IEEE Trans. Mob. Comput. 2025, 24, 5569–5583.
- 27.
Zhao, J.; Zhu, H.; Wang, F.; et al. PVD-FL: A privacy-preserving and verifiable decentralized federated learning framework. IEEE Trans. Inf. Forensics Secur. 2022, 17, 2059–2073.
- 28.
Xiu, R.; Le, J.; Zhang, D.; et al. Neuron Membership Inference Attack in Federated Learning for bit Scenarios. IEEE Trans. Emerg. Top. Comput. Intell. 2026, 10, 1849–1862.
- 29.
Lian, Z.; Yang, Q.; Wang, W.; et al. DEEP-FEL: Decentralized, efficient and privacy-enhanced federated edge learning for healthcare cyber physical systems. IEEE Trans. Netw. Sci. Eng. 2022, 9, 3558–3569.
- 30.
Li, H.; Lu, Q.; Chen, G.; et al. Distributed Constrained Optimization Over Unbalanced Directed Networks Using Asynchronous Broadcast-Based Algorithm. IEEE Trans. Autom. Control 2021, 66, 1102–1115.
- 31.
Li, Z.; Zeng, X.; Xiao, Y.; et al. Pattern-sensitive local differential privacy for finite-range time-series data in mobile crowdsensing. IEEE Trans. Mob. Comput. 2024, 24, 1–14.
- 32.
Lian, Z.; Zeng, Q.; Wang, W.; et al. Blockchain-based two-stage federated learning with non-IID data in IoMT system. IEEE Trans. Comput. Soc. Syst. 2022, 10, 1701–1710.
- 33.
Li, B.; Schmidt, M.N.; Alstrøm, T.S.; et al. On the effectiveness of partial variance reduction in federated learning with heterogeneous data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada, 18–22 June 2023; pp. 3964–3973.
- 34.
Malinovsky, G.; Yi, K.; Richt´arik, P. Variance reduced proxskip: Algorithm, theory and application to federated learning. Adv. Neural Inf. Process. Syst. 2022, 35, 15176–15189.
- 35.
Huang, Z.; Huang, W.; Jawanpuria, P.; et al. Federated learning on Riemannian manifolds with differential privacy. Mach. Learn. 2026, 115, 84.
- 36.
Xu, S.; Hua, Z.; Zheng, Y. Federated Learning in the Shuffle Model of Differential Privacy: A Communication-Efficient and Maliciously Secure Realization. IEEE Trans. Dependable Secur. Comput. 2026, 23, 6311–6329.
- 37.
Asad, M.; Shaukat, S.; Javanmardi, E.; et al. Secure and efficient blockchain-based federated learning approach for VANETs. IEEE Internet Things J. 2023, 11, 9047–9055.
- 38.
Lian, Z.; Wang, W.; Han, Z.; et al. Blockchain-based personalized federated learning for internet of medical things. IEEE Trans. Sustain. Comput. 2023, 8, 694–702.
- 39.
Nowroozi, E.; Haider, I.; Taheri, R.; et al. Federated Learning Under Attack: Exposing Vulnerabilities through Data Poisoning Attacks in Computer Networks. IEEE Trans. Netw. Serv. Manag. 2025, 22, 822–831.
- 40.
Yang, L.; Miao, Y.; Liu, Z.; et al. Enhanced model poisoning attack and multi-strategy defense in federated learning. IEEE Trans. Inf. Forensics Secur. 2025, 20, 3877–3892.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com