mlsanityData to 7 Oct 2026

Decentralized Inference with Graph Neural Networks in Wireless Communication Systems

arXiv 2104.09027 ↗First posted 19 Apr 2021cs.IT cs.LG math.ITcited by 18

Not on the map. Why?

Abstract (arXiv)

Graph neural network (GNN) is an efficient neural network model for graph data and is widely used in different fields, including wireless communications. Different from other neural network models, GNN can be implemented in a decentralized manner with information exchanges among neighbors, making it a potentially powerful tool for decentralized control in wireless communication systems. The main bottleneck, however, is wireless channel impairments that deteriorate the prediction robustness of GNN. To overcome this obstacle, we analyze and enhance the robustness of the decentralized GNN in different wireless communication systems in this paper. Specifically, using a GNN binary classifier as an example, we first develop a methodology to verify whether the predictions are robust. Then, we analyze the performance of the decentralized GNN binary classifier in both uncoded and coded wireless communication systems. To remedy imperfect wireless transmission and enhance the prediction robustness, we further propose novel retransmission mechanisms for the above two communication systems, respectively. Through simulations on the synthetic graph data, we validate our analysis, verify the effectiveness of the proposed retransmission mechanisms, and provide some insights for practical implementation.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 35 of its 50 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

35 of 50 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  4. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  5. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  6. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 408
  8. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 407
  9. 2018Adversarial Attack on Graph Structured Datacited by 300
  10. 2017An Introduction to Deep Learning for the Physical Layercited by 227
  11. 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
  12. 2018Deep Multi-View Spatial-Temporal Network for Taxi Demand Predictioncited by 162
23 more
  1. 2019A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problemscited by 157
  2. 2017Learning to Optimize: Training Deep Neural Networks for Wireless Resource Managementcited by 96
  3. 2019Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocationcited by 93
  4. 2019Optimal Wireless Resource Allocation with Random Edge Graph Neural Networkscited by 90
  5. 2019Graph Neural Networks for Decentralized Multi-Robot Path Planningcited by 84
  6. 2020Convergence Time Optimization for Federated Learning over Wireless Networkscited by 81
  7. 2020Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysiscited by 80
  8. 2019Learning Decentralized Controllers for Robot Swarms with Graph Neural Networkscited by 62
  9. 2019Certifiable Robustness to Graph Perturbationscited by 62
  10. 2019Certifiable Robustness and Robust Training for Graph Convolutional Networkscited by 59
  11. 2020Iterative Algorithm Induced Deep-Unfolding Neural Networks: Precoding Design for Multiuser MIMO Systemscited by 43
  12. 2020Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studiescited by 42
  13. 2019Accelerating DNN Training in Wireless Federated Edge Learning Systemscited by 34
  14. 2018Spatial Deep Learning for Wireless Schedulingcited by 32
  15. 2019Graph Embedding based Wireless Link Scheduling with Few Training Samplescited by 30
  16. 2020Fast Learning of Graph Neural Networks with Guaranteed Generalizability: One-hidden-layer Casecited by 24
  17. 2017Machine Learning for Networking: Workflow, Advances and Opportunitiescited by 20
  18. 2017An Iterative BP-CNN Architecture for Channel Decodingcited by 18
  19. 2020Graph Neural Networks for Decentralized Controllerscited by 14
  20. 2019GraphSAC: Detecting anomalies in large-scale graphscited by 11
  21. 2018Wireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmissioncited by 10
  22. 2016Big Data Caching for Networking: Moving from Cloud to Edgecited by 8
  23. 2017Unifying local and non-local signal processing with graph CNNscited by 3

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 3; 2023: 6; 2024: 3; 2025: 3.

18 papers.

Sort:

  1. 2022Task-Oriented Sensing, Computation, and Communication Integration for Multi-Device Edge AIcited by 31
  2. 2021Graph-based Deep Learning for Communication Networks: A Surveycited by 21
  3. 2023Machine Learning for Large-Scale Optimization in 6G Wireless Networkscited by 18
  4. 2021Modular Meta-Learning for Power Control via Random Edge Graph Neural Networkscited by 13
  5. 2021A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policiescited by 11
  6. 2022Graph Neural Networks Meet Wireless Communications: Motivation, Applications, and Future Directionscited by 8
  7. 2023A Survey on Trustworthy Edge Intelligence: From Security and Reliability To Transparency and Sustainabilitycited by 7
  8. 2023Rate-Adaptive Coding Mechanism for Semantic Communications With Multi-Modal Datacited by 6
  9. 2022Privacy-Preserving Decentralized Inference with Graph Neural Networks in Wireless Networkscited by 5
  10. 2023Semi-decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge-Computing Approachcited by 5
  11. 2024Collaborative Edge AI Inference over Cloud-RANcited by 5
  12. 2023Model Inversion Attacks on Homogeneous and Heterogeneous Graph Neural Networkscited by 2
6 more
  1. 2023Graph Neural Networks-Based User Pairing in Wireless Communication Systemscited by 1
  2. 2025Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning Approachcited by 1
  3. 2024Graph Neural Networks for Physical-Layer Security in Multi-User Flexible-Duplex Networkscited by 0
  4. 2024Deploying Graph Neural Networks in Wireless Networks: A Link Stability Viewpointcited by 0
  5. 2025Over-the-Air Multi-Sensor Inference with Neural Networks Using Memristor-Based Analog Computingcited by 0
  6. 2025Graph Attention Network for Optimal User Association in Wireless Networkscited by 0