JMLIS/
Articles/
2510001733
  • Open Access
  • Article

FedFE: A Fairness-Equilibrium Framework for Federated Learning Systems

  • Yuncheng Ge 1, †,   
  • Hanlin Li 1, †,   
  • Huiwei Wang 1, 2, *

Received: 13 Aug 2025 | Revised: 16 Sep 2025 | Accepted: 16 Oct 2025 | Published: 27 Oct 2025

Abstract

With the growing importance of data privacy and the tightening of security regulations, traditional centralized machine learning faces increasing scrutiny due to the need for direct data aggregation. Federated learning (FL) has emerged as a promising alternative, enabling collaborative model training while preserving data privacy by keeping raw data on local devices. Despite its advantages, fairness in FL remains a pressing challenge: disparities in data quality, quantity, and distribution among clients can lead to inequitable outcomes, discourage participation, and even give rise to free-rider problems. Existing research on FL fairness often lacks a holistic and precise methodology, tending to focus primarily on mitigating non-IID effects without adequately balancing fairness with other critical factors such as training efficiency and model accuracy. To address these limitations, this paper proposes a novel fair aggrega- tion framework for FL that jointly ensures internal and external gradient balance while enforcing equitable resource allocation. Our approach further integrates a momentum decay mechanism to accelerate convergence without compromising fairness. Extensive experiments on multiple benchmark datasets validate the effectiveness of the proposed framework, demonstrating consistent improvements in both accuracy and fairness compared to existing baselines.

References 

  • 1.
    McMahan, B.; Moore, E.; Ramage, D.; et al. Communication-efficient learning of deep networks from decentralized data. In Proceedings of the Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, 20–22 April 2017; pp. 1273–1282.
  • 2.
    Chen, J.; Pan, X.; Monga, R.; et al. Revisiting Distributed Synchronous SGD. In Proceedings of International Conference on Learning Representations (ICLR) Workshop Track, San Juan, PR, USA, 2–4 May 2016.
  • 3.
    Hashimoto, T.; Srivastava, M.; Namkoong, H.; et al. Fairness Without Demographics in Repeated Loss Minimization. In Proceedings of the International Conference on Machine Learning, Stockholm, Sweden, 10–15 July 2018; pp. 1929–1938.
  • 4.
    Zhao, Y.; Li, M.; Lai, L.; et al. Federated learning with non-iid data. arXiv 2018, arXiv:1806.00582.
  • 5.
    Liu, W.; Chen, L.; Chen, Y.; et al. Accelerating Federated Learning via Momentum Gradient Descent. IEEE Trans. Parallel Distrib. Syst. 2020, 31, 1754–1766.
  • 6.
    Li, T.; Sanjabi, M.; Beirami, A.; et al. Fair resource allocation in federated learning. In Proceedings of the International Conference on Learning Representations, 26 April–1 May 2020.
  • 7.
    Wang, Z.; Fan, X.; Qi, J.; et al. Federated learning with fair averaging.In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, Montreal, QC, Canada, 21–26 August 2021; pp. 1615–1623.
  • 8.
    Mohri, M.; Sivek, G.; Suresh, A.T.; et al. Agnostic Federated Learning. In Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA, 9–15 June 2019; pp. 4615–4625.
  • 9.
    Shi, Z.; Zhang, L.; Yao, Z.; et al. FedFAIM: A Model Performance-Based Fair Incentive Mechanism for Federated Learning. IEEE Trans. Big Data 2024, 10, 1038–1050.
  • 10.
    Hu, Z.; Shaloudegi, K.; Zhang, G.; et al. Federated Learning Meets Multi-Objective Optimization. IEEE Trans. Netw. Sci. Eng. 2022, 9, 2039–2051.
  • 11.
    Zhang, F.; Shuai, Z.; Kuang, K.; et al. Unified Fair Federated Learning for Digital Healthcare. Patterns 2024, 5, 100907.
  • 12.
    Liu, H.; Lu, J.; Wang, X.; et al. FedUP: Bridging Fairness and Efficiency in Cross-Silo Federated Learning. IEEE Trans. Serv. Comput. 2024, 17, 3672–3684.
  • 13.
    Ezzeldin, Y.; Yan, S.; He, C.; et al. Fairfed: Enabling group fairness in federated learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA, 7–14 February 2023; pp. 7494–7502.
  • 14.
    Li, J.; Zhu, T.; Ren, W.; et al. Improve individual fairness in federated learning via adversarial training. Comput. Secur. 2023, 132, 103336.
  • 15.
    Badar, M.; Nejdl, W.; Fisichella, M. FAC-fed: Federated adaptation for fairness and concept drift aware stream classification. Mach. Learn. 2023, 112, 2761–2786.
  • 16.
    Xu, H.; Gao, S.; Zhu, J. Harmony in Diversity: Personalized Federated Learning Against Statistical Hetero- geneity via a De-Personalized Feature Process. Expert Syst. Appl. 2025, 290, 128323.
  • 17.
    Nishio, T.; Shinkuma, R.; Mandayam, N.B.; et al. Estimation of Individual Device Contributions for Incentiviz- ing Federated Learning. In Proceedings of the 2020 IEEE Globecom Workshops (GC Wkshps), 7–11 December 2020; pp. 1–6.
  • 18.
    Jiang, Z.; Xu, J.; Zhang, S.; et al. FedCFA: Alleviating Simpson’s Paradox in Model Aggregation with Counter- factual Federated Learning. In Proceedings of the AAAI Conference on Artificial Intelligence, Philadelphia, PA, USA, 25 February–4 March 2025; pp. 17662–17670.
  • 19.
    Li, H.; Li, X.; Liu, X.; et al. FedSam: Enhancing federated learning accuracy with differential privacy and data heterogeneity mitigation. Comput. Stand. Interfaces 2025, 95,104019.
  • 20.
    Kuo, T.; Gabriel, R.; Koola, J.; et al. Distributed cross-learning for equitable federated models-privacy- preserving prediction on data from five California hospitals. Nat. Commun. 2025, 16, 1371.
  • 21.
    Wang, Z.; Peng, Z.; Fan, X.; et al. FedAVE: Adaptive data value evaluation framework for collaborative fairness in federated learning. Neurocomputing 2024, 574, 127227.
  • 22.
    Hu, J.; Zhang, H. FGS-FL: Enhancing federated learning with differential privacy via flat gradient stream. Expert Syst. Appl. 2025, 288, 128273.
  • 23.
    Hari, P.; Singh, M. Adaptive knowledge transfer using federated deep learning for plant disease detection. Comput. Electron. Agric. 2025, 229, 109720.
  • 24.
    Rahmati, M.; Pagano, A. Federated Learning-Driven Cybersecurity Framework for IoT Networks with Privacy Preserving and Real-Time Threat Detection Capabilities. Informatics 2025, 12, 62.
  • 25.
    Yu T.; Kumar S.; Gupta A.; et al. Gradient surgery for multi-task learning. In Proceedings of Advances in Neural Information Processing Systems, 6–12 December 2020; pp. 5824–5836.
  • 26.
    Ning, Q. On the momentum term in gradient descent learning algorithms. Neural Netw. 1999, 12, 145–151.
  • 27.
    Fernandes, M.; Silva, C.; Arrais, J.; et al. Decay Momentum for Improving Federated Learning. In Proceedings of the ESANN, 14–16 April 2021.
Share this article:
Download PDF
Issue
Volume 1, Issue 1
How to Cite
Ge, Y.; Li, H.; Wang, H. FedFE: A Fairness-Equilibrium Framework for Federated Learning Systems. Journal of Machine Learning and Information Security 2025, 1 (1), 4.
RIS
BibTex
Copyright & License
article copyright Image
Copyright (c) 2025 by the authors.