From Graphs to Qubits: A Critical Review of Quantum Graph Neural Networks

TL;DR

The paper addresses the scalability and optimization challenges of classical GNNs by surveying Quantum Graph Neural Networks (QGNNs), which embed graph structure into quantum circuits and variational procedures. It surveys a taxonomy of QGNN architectures (recurring, convolutional, spectral, spatial–temporal, graph-state–based, and equivariant variants) and details how Ising-model mappings, Hamiltonian dynamics, and variational frameworks are leveraged to learn from graph data. It highlights applications across high-energy physics, chemistry, complex systems, finance, and sensor networks, while clarifying obstacles like noise, scalability, lack of guarantees, and barren plateaus, and offering remediation ideas such as topology-aware synthesis and hybrid quantum–classical designs. The review emphasizes potential quantum advantages in learning dynamical graphs and quantum data, but stresses that practical impact awaits advances in hardware, error mitigation, and principled initialization and training strategies. Overall, QGNNs emerge as a promising but still nascent field that could enable quantum-accelerated graph learning and quantum-inspired representations for complex, networked systems.

Abstract

Quantum Graph Neural Networks (QGNNs) represent a novel fusion of quantum computing and Graph Neural Networks (GNNs), aimed at overcoming the computational and scalability challenges inherent in classical GNNs that are powerful tools for analyzing data with complex relational structures but suffer from limitations such as high computational complexity and over-smoothing in large-scale applications. Quantum computing, leveraging principles like superposition and entanglement, offers a pathway to enhanced computational capabilities. This paper critically reviews the state-of-the-art in QGNNs, exploring various architectures. We discuss their applications across diverse fields such as high-energy physics, molecular chemistry, finance and earth sciences, highlighting the potential for quantum advantage. Additionally, we address the significant challenges faced by QGNNs, including noise, decoherence, and scalability issues, proposing potential strategies to mitigate these problems. This comprehensive review aims to provide a foundational understanding of QGNNs, fostering further research and development in this promising interdisciplinary field.

Figures (9)

• Figure 1: Main scheme of the review.
• Figure 2: Illustration of node-classification and graph-classification tasks
• Figure 3: Illustration of qubit states on the Bloch Sphere.
• Figure 4: Scheme of a hybrid quantum-classical VQC for supervised learning.
• Figure 5: A single layer of a simple GNN. A graph is the input, and each component (V,E,U) gets updated by a MLP (classical computing) or by a VQA (quantum computing) to produce a new graph. Each function subscript indicates a separate function for a different graph attribute at the $n$-th layer of a GNN model.