CHALLENGES IN CENTRALIZED FEDERATED LEARNING
DOI:
https://doi.org/10.47390/ts-v4i1y2026N03Keywords:
federated learning, decentralized learning, network, privacy preservation, Internet of Things (IoT).Abstract
Federated Learning (FL) has recently attracted increasing attention due to its ability to enable knowledge sharing while preserving user data, protecting privacy, improving learning efficiency, and reducing communication overhead. Unlike Centralized Federated Learning (CFL), Decentralized Federated Learning (DFL) is based on a decentralized network architecture that eliminates the need for a central server. DFL enables direct communication among clients, thereby significantly reducing communication resource consumption.
References
1. P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. N.Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings et al.,“Advances and open problems in federated learning,” Found. Trends Mach. Learn., vol. 14, no. 1–2, pp. 1–210, Jun. 2021.
2. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial intelligence and statistics. PMLR, 2017, pp.1273–1282.
3. A. Hard, K. Rao, R. Mathews, S. Ramaswamy, F. Beaufays, S. Augenstein, H. Eichner, C. Kiddon, and D. Ramage, “Federated learning formobile keyboard prediction,” arXiv preprint arXiv:1811.03604, 2018.
4. D. Ramage and S. Mazzocchi, “Federated analytics: Collaborative data science without data collection,” Google Research, 2020.
5. D. Wang, S. Shi, Y. Zhu, and Z. Han, “Federated analytics: Opportunities and challenges,” IEEE Network, vol. 36, no. 1, pp. 151–158,2021.
6. A. R. Elkordy, Y. H. Ezzeldin, S. Han, S. Sharma, C. He, S. Mehrotra, S. Avestimehr et al., “Federated analytics: A survey,” APSIPA Transactions on Signal and Information Processing, vol. 12, no. 1, 2023.
7. D. Chen, D. Wang, Y. Zhu, and Z. Han, “Digital twin for federated analytics using a bayesian approach,” IEEE Internet of Things Journal,vol. 8, no. 22, pp. 16301–16312, 2021.
8. S. R. Pandey, M. N. Nguyen, T. N. Dang, N. H. Tran, K. Thar, Z. Han, and C. S. Hong, “Edge-assisted democratized learning toward federated analytics,” IEEE Internet of Things Journal, vol. 9, no. 1, pp. 572–588,2021.
9. Z. Wang, Y. Zhu, D. Wang, and Z. Han, “FedFPM: A unified federated analytics framework for collaborative frequent pattern mining,” in IEEE INFOCOM 2022-IEEE Conference on Computer Communications. IEEE, 2022, pp. 61–70.
10. D. Froelicher, J. R. Troncoso-Pastoriza, J. L. Raisaro, M. A. Cuendet, J. S. Sousa, H. Cho, B. Berger, J. Fellay, and J.-P. Hubaux, “Truly privacy-preserving federated analytics for precision medicine with multiparty homomorphic encryption,” Nature communications, vol. 12, no. 1, p. 5910, 2021.
11. Z. Wang, R. Gupta, K. Han, H. Wang, A. Ganlath, N. Ammar, and P. Tiwari, “Mobility digital twin: Concept, architecture, case study, and future challenges,” IEEE Internet Things J., Mar. 2022.
12. L. U. Khan, W. Saad, Z. Han, E. Hossain, and C. S. Hong, “Federated learning for internet of things: Recent advances, taxonomy, and open challenges,” IEEE Communications Surveys & Tutorials, vol. 23, no. 3, pp. 1759–1799, 2021.
13. Y. Li, B. Dang, W. Li, and Y. Zhang, “Glh-water: A large-scale dataset for global surface water detection in large-size very-high-resolution satellite imagery,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 20, 2024, pp. 22213–22221.
This work is licensed under a 