Privacy-Utility-Efficiency Trade-Offs in Personalized Federated Learning for Edge Computing
Clipping-Pressure Diagnostics and Pareto Operating Points for Privacy-Preserving Edge Learning
Received: 28 December 2025 | Revised: 21 January 2026 and 7 February 2026 | Accepted: 8 February 2026 | Online: 15 February 2026
Corresponding author: Mahavir Teraiya
Abstract
For the edge applications of Industrial Internet of Things (IIoT), the task of learning from distributed and privacy-conscious data needs to be conducted under constrained communication resources and in the presence of highly heterogeneous clients. This paper offers a personalized Federated Learning (FL) solution where the global backbone can be decoupled from the per-client heads, enabling the concurrent execution of global representation learning and local adaptation, even with non-Independent and Identically Distributed (non-IID) data. Differential Privacy (DP) is used to ensure privacy protection, where the updates of the backbone are differentially privatized via clipping and Gaussian noise, with the total privacy budget (ε, δ) measured over the number of communication rounds via a Rényi Differential Privacy (RDP) accountant. This study also provides a set of training diagnostics related to clipping pressure, including the proportion of clipped clients and the dynamics of the norms of the updates, which can identify the points at which privacy noise begins to dominate the learning process, along with privacy-friendly operating configurations. Experimental results on the LEAF and FEMNIST datasets reveal higher average accuracy and a narrower per-client accuracy distribution than those of the FL counterparts, whereas the privacy–utility–efficiency analysis identifies Pareto points at which privacy can be improved with a constant per-round communication cost, since only the backbone updates are communicated. In practice, this means more reliable performance at the client level for controlled privacy loss and predictable communication overheads, which makes this approach appropriate for edge sites with varying quality and availability of data.
Keywords:
edge computing, Federated Learning (FL), Differential Privacy (DP), personalized learning, non-IID dataDownloads
References
Ch.Ellaji, R. S. Ponmagal, and V. Saritha, "IDMO: A Multi-Stage Optimized Deep Learning Framework for Efficient and Scalable IoT Big Data Analytics," International Journal of Electronics and Communication Engineering, vol. 12, no. 11, pp. 8–20, Nov. 2025.
Z. Y. Lim, Y. H. Pang, S. Y. Ooi, W. H. Khoh, and Y. J. Chew, "NeuroFed-LightTCN: Federated Lightweight Temporal Convolutional Networks for Privacy-Preserving Seizure Detection in EEG Data," Applied Sciences, vol. 15, no. 17, Sept. 2025, Art. no. 9660.
A. Alhindi, S. Al-Ahmadi, and M. Maher Ben Ismail, "Balancing Privacy and Utility in Split Learning: An Adversarial Channel Pruning-Based Approach," IEEE Access, vol. 13, pp. 10094–10110, 2025.
X. Sheng, C. Yu, Y. Zhou, and X. Cui, "Reputation-Driven Asynchronous Federated Learning for Optimizing Communication Efficiency in Big Data Labeling Systems," Mathematics, vol. 12, no. 18, Sept. 2024, Art. no. 2932.
Y. Xu, B. Zhao, H. Zhou, and J. Su, "FedAdaSS: Federated Learning with Adaptive Parameter Server Selection Based on Elastic Cloud Resources," Computer Modeling in Engineering & Sciences, vol. 141, no. 1, pp. 609–629, Aug. 2024.
M. G. Hegde, B. Ruthvika, R. B. Jain, P. D. Shenoy, K. R. Venugopal, and A. Canchi, "A Privacy-Preserving Federated Learning Method with Homomorphic Encryption for Chronic Kidney Disease Stage Prediction," Engineering, Technology & Applied Science Research, vol. 15, no. 4, pp. 26019–26026, Aug. 2025.
W. Qian, Q. Shen, X. Chen, C. Li, Y. Fang, and Z. Wu, "FDP-FL: differentially private federated learning with flexible privacy budget allocation," The Computer Journal, vol. 67, no. 12, pp. 3180–3195, Dec. 2024.
V. S. Sadlapur and N. Hegde, "A Privacy-Preserving Reliable Authentication Scheme for 6G-Enabled Internet of Vehicular Edge Computing Networks," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 28810–28817, Dec. 2025.
W. Du, M. Li, L. Wu, Y. Han, T. Zhou, and X. Yang, "A efficient and robust privacy-preserving framework for cross-device federated learning," Complex & Intelligent Systems, vol. 9, no. 5, pp. 4923–4937, Oct. 2023.
M. A. P. Chamikara, P. Bertok, I. Khalil, D. Liu, and S. Camtepe, "Privacy preserving distributed machine learning with federated learning," Computer Communications, vol. 171, pp. 112–125, Apr. 2021.
D. Ye, R. Yu, M. Pan, and Z. Han, "Federated Learning in Vehicular Edge Computing: A Selective Model Aggregation Approach," IEEE Access, vol. 8, pp. 23920–23935, 2020.
Y. Zhang, H. Zhang, Y. Yang, W. Sun, H. Zhang, and Y. Fu, "Adaptive differential privacy in asynchronous federated learning for aerial-aided edge computing," Journal of Network and Computer Applications, vol. 235, Mar. 2025, Art. no. 104087.
Y. Song, D. He, M. Dai, and M. Guizani, "Cost-Efficient and Privacy-Preserving Distributed Learning: A Double Layer-Based Auction Design," IEEE Transactions on Mobile Computing, vol. 24, no. 9, pp. 8824–8840, Sept. 2025.
Y. Wan, Y. Qu, L. Gao, and Y. Xiang, "Privacy-preserving blockchain-enabled federated learning for B5G-Driven edge computing," Computer Networks, vol. 204, Feb. 2022, Art. no. 108671.
X. Zhao, Y. Wu, T. Zhao, F. Wang, and M. Li, "Federated deep reinforcement learning for task offloading and resource allocation in mobile edge computing-assisted vehicular networks," Journal of Network and Computer Applications, vol. 229, Sept. 2024, Art. no. 103941.
Y. Tao et al., "Private Over-the-Air Federated Learning at Band-Limited Edge," IEEE Transactions on Mobile Computing, vol. 23, no. 12, pp. 12444–12460, Dec. 2024.
Z. Lian, J. Cao, Q. Cao, W. Liu, Z. Zhu, and X. Zhou, "NebulaFL: Self-Organizing Efficient Multilayer Federated Learning Framework With Adaptive Load Tuning in Heterogeneous Edge Systems," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 43, no. 11, pp. 3358–3369, Nov. 2024.
M. Chahoud, S. Otoum, and A. Mourad, "On the feasibility of Federated Learning towards on-demand client deployment at the edge," Information Processing & Management, vol. 60, no. 1, Jan. 2023, Art. no. 103150.
Q. Yu, H. Xue, C. Wu, Y. Liu, and W. Guo, "Yardstick-Stackelberg pricing-based incentive mechanism for Federated Learning in Edge Computing," Computer Networks, vol. 262, May 2025, Art. no. 111186.
Y. Shi et al., "Efficient Federated Learning With Enhanced Privacy via Lottery Ticket Pruning in Edge Computing," IEEE Transactions on Mobile Computing, vol. 23, no. 10, pp. 9946–9958, Oct. 2024.
S. Caldas et al., "LEAF: A Benchmark for Federated Settings." arXiv, Dec. 09, 2019.
Downloads
How to Cite
License
Copyright (c) 2026 Mahavir Teraiya, Madhu Shukla
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
