Massive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning
IEEE Journal on Selected Areas in Communications · 2024-11 · 42 (11) · 3078-3094
DOI: 10.1109/jsac.2024.3431572 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Journal on Selected Areas in Communications, 2024-11. Verfasst von Li Qiao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 63-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Beijing Nova Program.
Abstract (Originalsprache)
Over-the-air computation (AirComp) is a promising technology converging communication and computation over wireless networks, which can be particularly effective in model training, inference, and more emerging edge intelligence applications. AirComp relies on uncoded transmission of individual signals, which are added naturally over the multiple access channel thanks to the superposition property of the wireless medium. Despite significantly improved communication efficiency, how to accommodate AirComp in the existing and future digital communication networks, that are based on discrete modulation schemes, remains a challenge. This paper proposes a massive digital AirComp (MD-AirComp) scheme, that leverages an unsourced massive access protocol, to enhance compatibility with both current and next-generation wireless networks. MD-AirComp utilizes vector quantization to reduce the uplink communication overhead, and employs shared quantization and modulation codebooks. At the receiver, we propose a near-optimal approximate message passing-based algorithm to compute the model aggregation results from the superposed sequences, which relies on estimating the number of devices transmitting each code sequence, rather than trying to decode the messages of individual transmitters. We apply MD-AirComp to federated edge learning (FEEL), and show that it significantly accelerates FEEL convergence compared to state-of-the-art while using the same amount of communication resources.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
- Beijing Nova Program
- UK Research and Innovation (UKRI) for the Projects Artificial Intelligence in the Air (AI-R) (European Research Council
- Sustainable Computing and Communication at the Edge
- Smart Networks and Services Joint Undertaking (SNS JU) Project 6G Goal Oriented AI-Enabled Learning and Semantic Communication Networks (6G-GOALS) under the EU…
- China Scholarship Council
Zitieren
APA
Qiao, L., Gao, Z., Mashhadi, M. B., & Gündüz, D. (2024). Massive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning. IEEE Journal on Selected Areas in Communications, 42(11), 3078-3094. https://doi.org/10.1109/jsac.2024.3431572
Vancouver
Qiao L, Gao Z, Mashhadi MB, Gündüz D. Massive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning. IEEE Journal on Selected Areas in Communications. 2024;42(11):3078-3094. doi:10.1109/jsac.2024.3431572
BibTeX
@article{Qiao2024,
author = {Qiao, Li and Gao, Zhen and Mashhadi, Mahdi Boloursaz and Gündüz, Deniz},
title = {Massive Digital Over-the-Air Computation for Communication-Efficient Federated Edge Learning},
journal = {IEEE Journal on Selected Areas in Communications},
year = {2024},
volume = {42},
number = {11},
pages = {3078--3094},
doi = {10.1109/jsac.2024.3431572}
}
EUVIMED