Data privacy is of great important in a big data society, and the traditional centralized machine learning faces severe scrutiny and check due to the risk of data leakage. Federated learning (FL) is a promising alternative to solve this problem as it is capable of 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. In other words, disparities in data quality, quantity and distribution (among clients) could produce inequitable outcomes, discourage participation, even give rise to free-rider problems. Existing FL research on fairness handling often lacks a holistic and precise methodology, and focuses primarily on mitigating none-independent identically distributed effects without adequately handling the fairness factors such as training efficiency and model accuracy. To fill in such a gap, this paper proposes a novel fair aggregation framework for FL to ensure both internal and external gradient balance, while enforcing equitable resource allocation. Furthermore, a momentum decay mechanism is integrated to accelerate the convergence speed without compromising fairness. Extensive experiments on multiple benchmark datasets validate the effectiveness of the proposed framework and compared to existing baselines, the proposed method demonstrates consistent improvement in both accuracy and fairness.
- Open Access
- Article
FedFE: A Fairness-Equilibrium Framework for Federated Learning Systems
- Yuncheng Ge 1, †,
- Hanlin Li 1, †,
- Huiwei Wang 1, 2, *
Author Information
Received: 13 Aug 2025 | Revised: 30 Sep 2025 | Accepted: 16 Oct 2025 | Published: 27 Oct 2025
Abstract
Keywords
federated learning | fairness | stability | efficiency | machine learning
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 8th International Conference on Learning Representations (ICLR 2020), Addis Ababa, Ethiopia, 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. Estimation of Individual Device Contributions for Incentivizing Federated Learning. In Proceedings of the 2020 IEEE Globecom Workshops (GC Wkshps), Taipei, Taiwan, 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. 2026, 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 the 34th Conference on Neural Information Processing Systems, Virtual, 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 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2021), Online, 6–8 October 2021.
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