An Overview on the Application of Graph Neural Networks in Wireless Networks
arXiv:2107.03029
Abstract
In recent years, with the rapid enhancement of computing power, deep learning methods have been widely applied in wireless networks and achieved impressive performance. To effectively exploit the information of graph-structured data as well as contextual information, graph neural networks (GNNs) have been introduced to address a series of optimization problems of wireless networks. In this overview, we first illustrate the construction method of wireless communication graph for various wireless networks and simply introduce the progress of several classical paradigms of GNNs. Then, several applications of GNNs in wireless networks such as resource allocation and several emerging fields, are discussed in detail. Finally, some research trends about the applications of GNNs in wireless communication systems are discussed.
arXiv comment17 pages, 14 figures, submitted to the IEEE Open Journal of the Communications Society. Manuscript received Jul. 29, 2021; revised Sept. 15, 2021; Oct. 25, 2021; accepted Nov. 12, 2021
References in corpus (32)
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Deep Convolutional Networks on Graph-Structured Data
- Convolutional Networks on Graphs for Learning Molecular Fingerprints
- Learning to Optimize: Training Deep Neural Networks for Wireless Resource Management
- Variational Graph Auto-Encoders
- Gated Graph Sequence Neural Networks
- Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
- Compressed Sensing using Generative Models
- How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
- Geom-GCN: Geometric Graph Convolutional Networks
- Equivariance Through Parameter-Sharing
- DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning
- Adaptive Graph Convolutional Neural Networks
- A Survey on The Expressive Power of Graph Neural Networks
- Learning Decentralized Wireless Resource Allocations with Graph Neural Networks
- ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
- Spectral-based Graph Convolutional Network for Directed Graphs
- A DRL-based Multiagent Cooperative Control Framework for CAV Networks: a Graphic Convolution Q Network
- Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
- Deep Learning on Knowledge Graph for Recommender System: A Survey
- A Review of Graph Neural Networks and Their Applications in Power Systems
- Leveraging the Capabilities of Connected and Autonomous Vehicles and Multi-Agent Reinforcement Learning to Mitigate Highway Bottleneck Congestion
- Graph Neural Networks for Massive MIMO Detection
- Channel Estimation for Full-Duplex RIS-assisted HAPS Backhauling with Graph Attention Networks
- Joint User Association and Power Allocation in Heterogeneous Ultra Dense Network via Semi-Supervised Representation Learning
- Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
- Topology Aware Deep Learning for Wireless Network Optimization
- Scalable Power Control/Beamforming in Heterogeneous Wireless Networks with Graph Neural Networks
- From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation