D2D Power Allocation via Quantum Graph Neural Network

TL;DR

Addresses scalable resource management in dense wireless networks by learning interference patterns with a fully quantum Graph Neural Network (QGNN) that passes messages via Parameterized Quantum Circuits. The approach encodes graph structure and performs end-to-end PQC-based message passing to optimize D2D power allocation for SINR maximization. On 300 channel realizations, the QGNN matches or exceeds WMMSE and yields about a 6% gain in sum-rate over a classical GCN with faster convergence and stronger generalization. This work demonstrates the potential of quantum-native graph learning for wireless optimization and points to future work on larger topologies, error mitigation, and hybrid training strategies.

Abstract

Increasing wireless network complexity demands scalable resource management. Classical GNNs excel at graph learning but incur high computational costs in large-scale settings. We present a fully quantum Graph Neural Network (QGNN) that implements message passing via Parameterized Quantum Circuits (PQCs). Our Quantum Graph Convolutional Layers (QGCLs) encode features into quantum states, process graphs with NISQ-compatible unitaries, and retrieve embeddings through measurement. Applied to D2D power control for SINR maximization, our QGNN matches classical performance with fewer parameters and inherent parallelism. This end-to-end PQC-based GNN marks a step toward quantum-accelerated wireless optimization.

Figures (2)

• Figure 1: The QGNN Architecture Overview.
• Figure 2: Models performance versus training epochs.