# Graph Neural Networks for Wireless Networks: Graph Representation, Architecture and Evaluation

arXiv: https://arxiv.org/abs/2404.11858 · HTML: https://mlsanity.com/paper/2404.11858/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2024.

## Built on by (most cited first, 7 of 7)

- [Generalization in Reinforcement Learning for Radio Access Networks](https://mlsanity.com/paper/2507.06602/) (2025)
- [Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey](https://mlsanity.com/paper/2601.03181/) (2026)
- [Digital Twin-Driven Pavement Health Monitoring and Maintenance Optimization Using Graph Neural Networks](https://mlsanity.com/paper/2511.02957/) (2025)
- [Power Allocation for Delay Optimization in Device-to-Device Networks: A Graph Reinforcement Learning Approach](https://mlsanity.com/paper/2505.12902/) (2025)
- [TrajAware: Graph Cross-Attention and Trajectory-Aware for Generalisable VANETs under Partial Observations](https://mlsanity.com/paper/2509.06665/) (2025)
- [Learning Wireless Interference Patterns: Decoupled GNN for Throughput Prediction in Heterogeneous Multi-Hop p-CSMA Networks](https://mlsanity.com/paper/2510.14137/) (2025)
- [RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches](https://mlsanity.com/paper/2511.20305/) (2025)

## Abstract (arXiv)

Graph neural networks (GNNs) have been regarded as the basic model to facilitate deep learning (DL) to revolutionize resource allocation in wireless networks. GNN-based models are shown to be able to learn the structural information about graphs representing the wireless networks to adapt to the time-varying channel state information and dynamics of network topology. This article aims to provide a comprehensive overview of applying GNNs to optimize wireless networks via answering three fundamental questions, i.e., how to input the wireless network data into GNNs, how to improve the performance of GNNs, and how to evaluate GNNs. Particularly, two graph representations are given to transform wireless network parameters into graph-structured data. Then, we focus on the architecture design of the GNN-based models via introducing the basic message passing as well as model improvement methods including multi-head attention mechanism and residual structure. At last, we give task-oriented evaluation metrics for DL-enabled wireless resource allocation. We also highlight certain challenges and potential research directions for the application of GNNs in wireless networks.