Federated Learning: From Origins to Modern Applications and Challenges

M. Bharathi; T. Aditya Sai Srinivas; M. Bhuvaneswari

doi:10.48001/joitc.2024.1229-38

Authors

M. Bharathi Department of Artificial Intelligence and Machine Learning, Jayaprakash Narayan College of Engineering, Dharmapur, Telangana, India
T. Aditya Sai Srinivas Department of Artificial Intelligence and Machine Learning, Jayaprakash Narayan College of Engineering, Dharmapur, Telangana, India
M. Bhuvaneswari Department of Artificial Intelligence and Machine Learning, Jayaprakash Narayan College of Engineering, Dharmapur, Telangana, India

DOI:

https://doi.org/10.48001/joitc.2024.1229-38

Keywords:

Collaborative model training, Data privacy, Decentralized machine learning, Federated Learning (FL), Scalability challenges

Abstract

Federated learning is an innovative machine learning approach that allows models to be trained collaboratively across decentralized data sources, all while keeping sensitive information where it belongs on local devices. This method has gained significant attention in recent years, primarily because it offers a way to address growing concerns around data privacy and security. Instead of collecting data in a central location, federated learning enables different entities, like hospitals or financial institutions, to work together on model training without ever sharing their raw data. This makes it particularly valuable in fields where privacy is paramount. This paper explores the evolution, applications, and challenges of federated learning, providing a well-rounded understanding of its potential. The benefits are clear: enhanced privacy, increased collaboration, and the ability to leverage diverse datasets. However, there are also challenges to be addressed, such as improving communication protocols, ensuring scalability, and developing stronger privacy-preserving techniques. By systematically reviewing literature from peer-reviewed journals and reputable sources, this study reveals that while federated learning offers a promising path forward, more research is needed to overcome its current limitations. Ultimately, this paper contributes to the growing body of knowledge on how federated learning can shape the future of secure and efficient decentralized learning.

Downloads

Download data is not yet available.

References

Abdul Rahman, S., Tout, H., Ould-Slimane, H., Mourad, A., Talhi, C., & Guizani, M. (2020). A survey on federated learning: The journey from centralized to distributed on-site learning and beyond. IEEE Internet of Things Journal, 8(7), 5476-5497. https://doi.org/10.1109/JIOT.2020.3030072.

Blanco-Justicia, A., Domingo-Ferrer, J., Martínez, S., Sánchez, D., Flanagan, A., & Tan, K. E. (2021). Achieving security and privacy in federated learning systems: Survey, research challenges and future directions. Engineering Applications of Artificial Intelligence, 106, 104468. https://doi.org/10.1016/j.engappai.2021.104468.

Chen, M., Shlezinger, N., Poor, H. V., Eldar, Y. C., & Cui, S. (2021). Communication-efficient federated learning. Proceedings of the National Academy of Sciences, 118(17), e2024789118. https://doi.org/10.1073/pnas.2024789118.

Goetz, J., Malik, K., Bui, D., Moon, S., Liu, H., & Kumar, A. (2019). Active federated learning. arXiv preprint arXiv:1909.12641. https://doi.org/10.48550/arXiv.1909.12641.

Kasturi, A., Ellore, A. R., & Hota, C. (2020). Fusion learning: A one shot federated learning. In Computational Science–ICCS 2020: 20th International Conference, Amsterdam, The Netherlands, June 3–5, 2020, Proceedings, Part III 20 (pp. 424-436). Springer International Publishing. https://doi.org/10.1007/978-3-030-50420-5_31.

Li, L., Fan, Y., Tse, M., & Lin, K. Y. (2020). A review of applications in federated learning. Computers & Industrial Engineering, 149, 106854. https://doi.org/10.1016/j.cie.2020.106854.

Lyu, L., Yu, H., Zhao, J., & Yang, Q. (2020). Threats to federated learning. Federated Learning: Privacy and Incentive, 3-16. https://doi.org/10.1007/978-3-030-63076-8_1.

Ma, X., Zhu, J., Lin, Z., Chen, S., & Qin, Y. (2022). A state-of-the-art survey on solving non-iid data in federated learning. Future Generation Computer Systems, 135, 244-258. https://doi.org/10.1016/j.future.2022.05.003.

Mammen, P. M. (2021). Federated learning: Opportunities and challenges. arXiv Preprint arXiv:2101.05428. https://doi.org/10.48550/arXiv.2101.05428.

Ziller, A., Trask, A., Lopardo, A., Szymkow, B., Wagner, B., Bluemke, E., ... & Kaissis, G. (2021). Pysyft: A library for easy federated learning. Federated Learning Systems: Towards Next-Generation AI, 111-139. https://doi.org/10.1007/978-3-030-70604-3_5.