HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks
IEEE Transactions on Mobile Computing · 01.11.2023 · 22 (11) · 6495-6507
DOI: 10.1109/tmc.2022.3190510 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, erschienen am 01.11.2023. Verfasst von Minh-Duong Nguyen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 46-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: National Research Foundation of Korea, Australian Research Council, BK21 Four.
Abstract (Originalsprache)
Federated learning (FL) is a new artificial intelligence concept that enables Internet-of-Things (IoT) devices to learn a collaborative model without sending the raw data to centralized nodes for processing. Despite numerous advantages, low computing resources at IoT devices and high communication costs for exchanging model parameters make applications of FL in massive IoT networks very limited. In this work, we develop a novel compression scheme for FL, called high-compression federated learning (HCFL), for very large scale IoT networks. HCFL can reduce the data load for FL processes without changing their structure and hyperparameters. In this way, we not only can significantly reduce communication costs, but also make intensive learning processes more adaptable on low-computing resource IoT devices. Furthermore, we investigate a relationship between the number of IoT devices and the convergence level of the FL model and thereby better assess the quality of the FL process. We demonstrate our HCFL scheme in both simulations and mathematical analyses. Our proposed theoretical research can be used as a minimum level of satisfaction, proving that the FL process can achieve good performance when a determined configuration is met. Therefore, we show that HCFL is applicable in any FL-integrated networks with numerous IoT devices.
Förderung
- National Research Foundation of Korea
- Australian Research Council
- BK21 Four
- Korean Southeast Center for the 4th Industrial Revolution Leader Education
- Institute of Information and Communications Technology Planning and Evaluation
Zitieren
APA
Nguyen, M., Lee, S., Pham, Q., Hoang, D. T., Nguyen, D. N., & Hwang, W. (2023). HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks. IEEE Transactions on Mobile Computing, 22(11), 6495-6507. https://doi.org/10.1109/tmc.2022.3190510
Vancouver
Nguyen M, Lee S, Pham Q, Hoang DT, Nguyen DN, Hwang W. HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks. IEEE Transactions on Mobile Computing. 2023;22(11):6495-6507. doi:10.1109/tmc.2022.3190510
BibTeX
@article{Nguyen2023,
author = {Nguyen, Minh-Duong and Lee, Sang-Min and Pham, Quoc-Viet and Hoang, Dinh Thai and Nguyen, Diep N. and Hwang, Won-Joo},
title = {HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks},
journal = {IEEE Transactions on Mobile Computing},
year = {2023},
volume = {22},
number = {11},
pages = {6495--6507},
doi = {10.1109/tmc.2022.3190510}
}
EUVIMED