mlsanityData to 7 Oct 2026

Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networks

arXiv 2302.08447 ↗First posted 16 Feb 2023eess.SP cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) model representations from networked data and allow for decentralized inference through localized communications. Existing GNN architectures 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. AirGNNs modify graph convolutional operations that shift graph signals over random communication graphs to take into account channel fading and noise when aggregating features from neighbors, thus, improving architecture robustness to channel impairments during testing. 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 and multi-robot flocking corroborate theoretical findings and show superior performance of AirGNNs over wireless communication channels.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 46 of its 92 references that are in the map. First posted on arXiv 16 Feb 2023.

Builds on

46 of 92 references.

References · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  4. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2018Session-based Recommendation with Graph Neural Networkscited by 312
  7. 2018Federated Learning via Over-the-Air Computationcited by 215
  8. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 186
  9. 2019Federated Learning over Wireless Fading Channelscited by 178
  10. 2019Stability Properties of Graph Neural Networkscited by 125
  11. 2018Convolutional Neural Network Architectures for Signals Supported on Graphscited by 94
  12. 2019Optimal Wireless Resource Allocation with Random Edge Graph Neural Networkscited by 90
34 more
  1. 2020Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysiscited by 80
  2. 2020Graph Neural Networks: Architectures, Stability and Transferabilitycited by 79
  3. 2020Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networkscited by 73
  4. 2019Learning Decentralized Controllers for Robot Swarms with Graph Neural Networkscited by 62
  5. 2020Blind Federated Edge Learningcited by 42
  6. 2020EdgeNets:Edge Varying Graph Neural Networkscited by 36
  7. 2019Machine Learning in the Aircited by 32
  8. 2021Interpretable Stability Bounds for Spectral Graph Filterscited by 28
  9. 2020Communicate to Learn at the Edgecited by 27
  10. 2019A Graph Neural Network Approach for Scalable Wireless Power Controlcited by 26
  11. 2021Link Scheduling using Graph Neural Networkscited by 26
  12. 2019Over-the-Air Computation Systems: Optimization, Analysis and Scaling Lawscited by 25
  13. 2021Learning Decentralized Wireless Resource Allocations with Graph Neural Networkscited by 24
  14. 2022Gradient and Channel Aware Dynamic Scheduling for Over-the-Air Computation in Federated Edge Learning Systemscited by 20
  15. 2022A Survey on Over-the-Air Computationcited by 19
  16. 2022Learning Resilient Radio Resource Management Policies with Graph Neural Networkscited by 17
  17. 2021Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networkscited by 14
  18. 2021Wide and Deep Graph Neural Network with Distributed Online Learningcited by 14
  19. 2019A New Framework for Multi-Agent Reinforcement Learning -- Centralized Training and Exploration with Decentralized Execution via Policy Distillationcited by 12
  20. 2020Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learningcited by 12
  21. 2020Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networkscited by 11
  22. 2021Hierarchical Over-the-Air Federated Edge Learningcited by 11
  23. 2022Over-the-Air Ensemble Inference with Model Privacycited by 9
  24. 2019Time Synchronization in 5G Wireless Edge: Requirements and Solutions for Critical-MTCcited by 7
  25. 2022Graph Neural Networks for Distributed Power Allocation in Wireless Networks: Aggregation Over-the-Aircited by 7
  26. 2022Over-the-Air Split Machine Learning in Wireless MIMO Networkscited by 7
  27. 2022Decentralized Channel Management in WLANs with Graph Neural Networkscited by 7
  28. 2020Balancing Rates and Variance via Adaptive Batch-Size for Stochastic Optimization Problemscited by 6
  29. 2020Efficient power allocation using graph neural networks and deep algorithm unfoldingcited by 6
  30. 2022Environment Optimization for Multi-Agent Navigationcited by 6
  31. 2022Learning Stochastic Graph Neural Networks with Constrained Variancecited by 5
  32. 2022Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networkscited by 5
  33. 2022Over-the-Air Computation over Balanced Numeralscited by 4
  34. 2020Amplify-and-Forward Relaying for Hierarchical Over-the-Air Computationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Stochastic Sequential Decision Making over Expanding Networks with Graph Filteringcited by 0
  2. 2026MANET-GNN: Learned Decentralized Optimization of Power Allocation in Multi-Channel MANETscited by 0