Federated Learning Unveiled: From Practical Insights to Bold Predictions

M. Bharathi; T. Aditya Sai Srinivas

doi:10.48001/joitml.2025.211-10

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

DOI:

https://doi.org/10.48001/joitml.2025.211-10

Keywords:

Collaborative machine learning, Differential Privacy (DP), Federated Learning (FL), Heterogeneous devices, Predictions

Abstract

Federated Learning (FL) is a collaborative machine learning technique that lets multiple entities train a shared model without exchanging their data, keeping privacy intact. Over the past decade, FL has evolved, scaling to millions of devices in various domains, all while maintaining strong differential privacy (DP) protections. Companies like Google, Apple, and Meta have successfully brought FL to life in their systems, proving its real-world value. However, challenges remain. Verifying server-side DP guarantees and managing training across a mix of device types are complex issues that need attention. Emerging trends like large multi-modal models and blurred lines between training and personalization are pushing traditional FL to its limits. To address these challenges, we propose a more flexible FL framework focused on privacy principles, using trusted execution environments and open-source collaboration to drive future innovation.

Downloads

References

Antonopoulos, N., & Gillam, L. (2010). Cloud computing (Vol. 51, No. 7). London: Springer. https://doi.org/10.1007/978-3-319-54645-2.

Baalamurugan, K. M., Vinotha, D., & Sivakumar, P. (2021). An efficient ant colony-based self-adaptive routing strategy for IoT network model. In International Conference on Communication, Computing and Electronics Systems: Proceedings of ICCCES 2020 (pp. 753-764). Springer Singapore. https://doi.org/10.1007/978-981-33-4909-4_60.

Baker, S. A., & Nori, A. S. (2021). Internet of things security: a survey. In Advances in Cyber Security: Second International Conference, ACeS 2020, Penang, Malaysia, December 8-9, 2020, Revised Selected Papers 2 (pp. 95-117). Springer Singapore. https://doi.org/10.1007/978-981-33-6835-4_7.

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.

Ge, H., Yang, X., Wang, J., & Lyu, Z. (2024). A decentralised federated learning scheme for heterogeneous devices in cognitive IoT. International Journal of Cognitive Computing in Engineering, 5, 357-366. https://doi.org/10.1016/j.ijcce.2024.08.001.

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.

Liu, D., Mao, Q., Gao, L., & Wang, G. (2024). Leveraging contrastive language–image pre-training and bidirectional cross-attention for multimodal keyword spotting. Engineering Applications of Artificial Intelligence, 138, 109403. https://doi.org/10.1016/j.engappai.2024.109403.

Liu, J., Huang, J., Zhou, Y., Li, X., Ji, S., Xiong, H., & Dou, D. (2022). From distributed machine learning to federated learning: A survey. Knowledge and Information Systems, 64(4), 885-917. https://doi.org/10.1007/s10115-022-01664-x.

Ramirez, T., Calabuig-Barbero, E., Mora, H., Pujol, F. A., & Amador, S. (2023, November). Federated Learning for Industry 5.0: A State-of-the-Art Review. In International Conference on Ubiquitous Computing and Ambient Intelligence (pp. 60-66). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-48590-9_6.

Stieninger, M., & Nedbal, D. (2014). Characteristics of cloud computing in the business context: A systematic literature review. Global Journal of Flexible Systems Management, 15, 59-68. https://doi.org/10.1007/s40171-013-0055-4.

Suliman, M., & Leith, D. (2023, September). Two models are better than one: Federated learning is not private for google gboard next word prediction. In European Symposium on Research in Computer Security (pp. 105-122). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-51482-1_6.

Ullah, Z., Al-Turjman, F., Mostarda, L., & Gagliardi, R. (2020). Applications of artificial intelligence and machine learning in smart cities. Computer Communications, 154, 313-323. https://doi.org/10.1016/j.comcom.2020.02.069.

Van Dijk, M., & Nguyen, P. H. (2024). Considerations on the theory of training models with differential privacy. In Federated Learning (pp. 29-55). Academic Press. https://doi.org/10.1016/B978-0-44-319037-7.00009-0.

Wen, J., Zhang, Z., Lan, Y., Cui, Z., Cai, J., & Zhang, W. (2023). A survey on federated learning: challenges and applications. International Journal of Machine Learning and Cybernetics, 14(2), 513-535. https://doi.org/10.1007/s13042-022-01647-y.

Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., & Gao, Y. (2021). A survey on federated learning. Knowledge-Based Systems, 216, 106775. https://doi.org/10.1016/j.knosys.2021.106775.