A Federated Learning Framework for Resource-Constrained Environments
Abstract
This paper presents a Federated Learning Framework adapted for resource-constrained environments, focusing on IoT devices. This is the first framework that enables federated training directly on microcontrollers. The framework demonstrates the autonomy of federated nodes, validating the feasibility of training models directly on microcontrollers. Two experiments were performed, showing promising results, despite challenges inherent to the environment, such as computational limitations, communicability, and scalability. Comparisons with related frameworks, such as TensorFlow-Federated, highlight the efficiency and dynamism of the proposed solution. The paper also discusses practical insights and improvements, contributing to the advancement of decentralized learning and the evolution of the TinyML scenario.
References
Ficco, M., Guerriero, A., Milite, E., Palmieri, F., Pietrantuono, R., and Russo, S. (2024). Federated learning for IoT devices: Enhancing tinyml with on-board training. Information Fusion, 104, 102189.
Li, H., Ota, K., and Dong, M. (2018). Learning IoT in edge: Deep learning for the internet of things with edge computing. IEEE Network, 32(1), 96–101.
Llisterri Giménez, N., Monfort Grau, M., Pueyo Centelles, R., and Freitag, F. (2022). On-device training of machine learning models on microcontrollers with federated learning. Electronics, 11(4).
Rai, P. and Rehman, M. (2019). ESP32 based smart surveillance system. In 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), 1–3.
Shi, W., Pallis, G., and Xu, Z. (2019). Edge computing [scanning the issue]. Proceedings of the IEEE, 107(8), 1474–1481.
Sun, T., Li, D., and Wang, B. (2023). Decentralized federated averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4289–4301.
Verbraeken, J., Wolting, M., Katzy, J., Kloppenburg, J., Verbelen, T., and Rellermeyer, J. S. (2020). A survey on distributed machine learning. ACM Computing Surveys, 53(2), 1–33.
Wang, P., Li, Y., and Reddy, C. K. (2017). Machine learning for survival analysis: A survey.
Wulfert, L., Wiede, C., and Grabmaier, A. (2023). TinyFL: On-device training, communication and aggregation on a microcontroller for federated learning. In 2023 21st IEEE Interregional NEWCAS Conference (NEWCAS), 1–5.
Zhang, C., Xie, Y., Bai, H., Yu, B., Li, W., and Gao, Y. (2021). A survey on federated learning. Knowledge-Based Systems, 216, 106775.
Čolaković, A. and Hadžialić, M. (2018). Internet of things (IoT): A review of enabling technologies, challenges, and open research issues. Computer Networks, 144, 17–39.
