Massive digital over-the-air computation for communication-efficient federated edge learning
File(s)
Accepted version
Author(s)
Qiao, Li
Gao, Zhen
Mashhadi, Mahdi Boloursaz
Gunduz, Deniz
Type
Journal Article
Abstract
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.
Date Issued
2024-11-01
Date Acceptance
2024-05-20
Citation
IEEE Journal on Selected Areas in Communications, 2024, 42 (11), pp.3078-3094
ISSN
0733-8716
Publisher
Institute of Electrical and Electronics Engineers
Start Page
3078
End Page
3094
Journal / Book Title
IEEE Journal on Selected Areas in Communications
Volume
42
Issue
11
Copyright Statement
Copyright © 2024 IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Subjects
Artificial intelligence
Artificial intelligence of things (AIoT)
Atmospheric modeling
Computational modeling
digital over-the-air computation
distributed optimization
Engineering
Engineering, Electrical & Electronic
federated edge learning
Modulation
Quantization (signal)
Science & Technology
Technology
Telecommunications
unsourced massive access
Vectors
Wireless networks
Publication Status
Published
Date Publish Online
2024-08-26