Scalable Quantum Message Passing Graph Neural Networks for Next-Generation Wireless Communications: Architectures, Use Cases, and Future Directions

TL;DR

This work introduces SQM-GNN, a scalable quantum message passing Graph Neural Network designed for next-generation wireless networks. By decomposing large graphs into fixed-size star-shaped subgraphs and applying a shared parameterized quantum circuit, SQM-GNN performs quantum-native message passing while incorporating both node and edge features, addressing NISQ hardware limits. In a device-to-device power control scenario, SQM-GNN outperforms classical GNNs and heuristic baselines in sum-rate performance and generalization, while maintaining linear training complexity with respect to the number of nodes, $\mathcal{O}(N)$. The approach offers a practical quantum-enhanced direction for real-time, topology-aware resource management in dense NG networks and points to future work in multi-task learning, privacy-preserving learning, and cross-domain adaptation.

Abstract

Graph Neural Networks (GNNs) are eminently suitable for wireless resource management, thanks to their scalability, but they still face computational challenges in large-scale, dense networks in classical computers. The integration of quantum computing with GNNs offers a promising pathway for enhancing computational efficiency because they reduce the model complexity. This is achieved by leveraging the quantum advantages of parameterized quantum circuits (PQCs), while retaining the expressive power of GNNs. However, existing pure quantum message passing models remain constrained by the limited number of qubits, hence limiting the scalability of their application to the wireless systems. As a remedy, we conceive a Scalable Quantum Message Passing Graph Neural Network (SQM-GNN) relying on a quantum message passing architecture. To address the aforementioned scalability issue, we decompose the graph into subgraphs and apply a shared PQC to each local subgraph. Importantly, the model incorporates both node and edge features, facilitating the full representation of the underlying wireless graph structure. We demonstrate the efficiency of SQM GNN on a device-to-device (D2D) power control task, where it outperforms both classical GNNs and heuristic baselines. These results highlight SQM-GNN as a promising direction for future wireless network optimization.

Figures (3)

• Figure 1: An overview of QPU-assisted NG communication architecture, where the QPU serves as a central resource management entity, connecting and coordinating multiple platforms.
• Figure 2: Comparison between the classical GNN architecture (top) and the SQM-GNN architecture (bottom).
• Figure 3: SQM-GNN application of power control in a D2D network.