On the Impact of Data Heterogeneity in Federated Learning: A Case Study on Air Quality Prediction
DOI:
https://doi.org/10.54097/rne84c68Keywords:
Federated Learning, Federated Averaging, FedProx, Air Quality Prediction.Abstract
Federated learning has become a popular model to apply in privacy-preserving modeling in distributed settings, particularly when the models are applied to data that is distributed among various locations and is often sensitive, such as in air quality prediction. This paper looks into how effective federated learning is for predicting ozone (O₃) concentrations, under both independent and non-independent data distributions. In particular, two representative algorithms Federated Averaging (FedAvg)and Federated Averaging (FedAvg) are experimented on a real-world air quality dataset. An experimental framework was established that was relatively comprehensive and centralized training and local-only models were used as baselines. Mean absolute error (MAE) and root mean squared error (RMSE) are used to measure model performance. The findings suggest that federated learning performs much better than the isolated local models and the performance is similar to that of the centralized training. Having said that, data heterogeneity does present certain issues-it slows down convergence and decreases accuracy in prediction. In such non-IID conditions, FedProx is more stable and less erroneous than FedAvg implying that it is more resistant to client drift.Most importantly, this paper provides empirical data on the impact of data heterogeneity on federated learning, and proves that federated learning can be a viable alternative in privacy-sensitive environmental prediction problems.
References
[1] Li J, Wang S. A comprehensive survey on energy-efficient and privacy-preserving federated learning for edge intelligence and IoT. Results in Engineering. 2025;28:107849.
[2] Gad E, et al. A robust federated learning approach for combating attacks against IoT systems under non-IID challenges. In: Proceedings of the International Conference on Smart Applications, Communications and Networking (SmartNets); 2024 May; Harrisonburg, VA, USA. p. 1–6.
[3] Singh A, Gupta R. Privacy-preserving and computationally efficient federated learning for household load estimation. Sustainable Computing: Informatics and Systems. 2025;42:101234.
[4] Sun Z, et al. A survey on federated recommendation systems. IEEE Transactions on Neural Networks and Learning Systems. 2025;36(1):6–20.
[5] McMahan B, et al. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS); 2017. p. 1273–1282.
[6] Li S, Giannakis GB, Sun Y. Federated optimization in heterogeneous networks. In: Proceedings of Machine Learning and Systems (MLSys); 2020.
[7] Zeng D, et al. On the power of adaptive weighted aggregation in heterogeneous federated learning. In: Proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS). 2025;258:1081–1089.
[8] Keerthika P, et al. Proximal guided hybrid federated learning approach with parameter-efficient adaptive intelligence for pneumonia diagnosis. Scientific Reports. 2025;16(1):2412.
[9] Karimireddy SP, et al. SCAFFOLD: Stochastic controlled averaging for federated learning. In: Proceedings of the International Conference on Machine Learning (ICML); 2020. p. 5132–5143.
[10] Li Q, He B, Song D. Model-contrastive federated learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR); 2021. p. 10713–10722.
[11] Wang H, Yurochkin M, Sun Y, Papailiopoulos D, Khazaeni Y. Federated learning with matched averaging. In: Proceedings of the International Conference on Learning Representations (ICLR); 2020.
[12] Zhao Y, et al. Federated learning with non-IID data. arXiv preprint. 2018;arXiv:1806.00582.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
