Graph neural networks over the air for decentralized tasks in wireless networks
File(s)GG_TSP25.pdf (1.07 MB)
Accepted version
Author(s)
Gao, Zhan
Gündüz, Deniz
Type
Journal Article
Abstract
Graph neural networks (GNNs) model representations from networked data and allow for decentralized execution through localized communications. Existing GNNs often assume ideal communications and ignore potential channel effects, such as fading and noise, leading to performance degradation in real-world implementation. Considering a GNN implemented over nodes connected through wireless links, this paper conducts a stability analysis to study the impact of channel impairments on the performance of GNNs, and proposes graph neural networks over the air (AirGNNs), a novel GNN architecture that incorporates the communication model and permits decentralized execution with over-the-air computation. AirGNNs modify graph convolutional operations that shift graph signals over random communication graphs to account for channel fading and noise when aggregating features from neighbors, thus, improving architecture robustness to channel impairments. We develop a channel-inversion signal transmission strategy for AirGNNs when channel state information (CSI) is available, and propose a stochastic gradient descent based method to train AirGNNs when CSI is unknown. The convergence analysis shows that the training procedure approaches a stationary solution of an associated stochastic optimization problem and the variance analysis characterizes the statistical behavior of the trained model. Experiments on decentralized source localization, multi-robot flocking and wireless channel management corroborate theoretical findings and show superior performance of AirGNNs over wireless communication channels.
Date Issued
2025-01-01
Date Acceptance
2025-01-01
Citation
IEEE Transactions on Signal Processing, 2025, 73, pp.721-737
ISSN
1053-587X
Publisher
Institute of Electrical and Electronics Engineers
Start Page
721
End Page
737
Journal / Book Title
IEEE Transactions on Signal Processing
Volume
73
Copyright Statement
Copyright © 2025 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
Publication Status
Published
Date Publish Online
2025-01-27