Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:1909.12264

Quantum Graph Neural Networks

Guillaume Verdon, Trevor McCourt, Luzhnica, Enxhell, Singh, Vikash, Stefan Leichenauer, Jack D. Hidary

Published Sep 26, 2019• 58 citations
arXivHTMLPDF

Abstract

We introduce Quantum Graph Neural Networks (QGNN), a new class of quantum neural network ansatze which are tailored to represent quantum processes which have a graph structure, and are particularly suitable to be executed on distributed quantum systems over a quantum network. Along with this general class of ansatze, we introduce further specialized architectures, namely, Quantum Graph Recurrent Neural Networks (QGRNN) and Quantum Graph Convolutional Neural Networks (QGCNN). We provide four example applications of QGNNs: learning Hamiltonian dynamics of quantum systems, learning how to create multipartite entanglement in a quantum network, unsupervised learning for spectral clustering, and supervised learning for graph isomorphism classification.

DOI
10.48550/arxiv.1909.12264

Related papers

A Tutorial on Quantum Graph Recurrent Neural Network (QGRNN)

Jaeho Choi, Seunghyeok Oh, Joongheon Kim

Over the past decades, various neural networks have been proposed with the rapid development of the machine learning field. In particular, graph neural networks using feature-vectors assigned to nodes and edges have been attracting attention in various fields. The usefulness of graph neural networks also affected the field of quantum computing, which led to the birth of quantum graph neural networks composed of parameterized quantum circuits. The quantum graph neural networks have many possibilities as applications from the simulation perspective of quantum dynamics. Among the application models of various quantum graph neural networks, the quantum graph recurrent neural network (QGRNN) is proven to be effective in training the Ising model Hamiltonian. Thus, this paper introduces the concepts of the Ising model, variational quantum eigensolver (VQE) for preparing quantum data, and QGRNN from a software engineer's point of view.

International Conference on Information Networking•Jan 13, 2021•22 citations

QGHNN: A Quantum Graph Hamiltonian Neural Network

Wenxuan Wang, Jinjing Shi, Nan Guan +2 more

Representing and learning from graphs is essential for developing effective machine learning models tailored to non-Euclidean data. While Graph Neural Networks (GNNs) strive to address the challenges posed by complex, high-dimensional graph data, Quantum Neural Networks (QNNs) present a compelling alternative due to their potential for quantum parallelism. However, much of the current QNN research tends to overlook the vital connection between quantum state encoding and graph structures, which limits the full exploitation of quantum computational advantages. To address these challenges, this paper introduces a quantum graph Hamiltonian neural network (QGHNN) to enhance graph representation and learning on noisy intermediate-scale quantum computers. Concretely, a quantum graph Hamiltonian learning method (QGHL) is first created by mapping graphs to the Hamiltonian of the topological quantum system. Then, QGHNN based on QGHL is presented, which trains parameters by minimizing the loss function and uses the gradient descent method to learn the graph. Experiments on the PennyLane quantum platform reveal that QGHNN outperforms all assessment metrics, achieving the lowest mean squared error of0.004and the maximum cosine similarity of99.8%, which shows that QGHNN not only excels in representing and learning graph information, but it also has high robustness ability. QGHNN can reduce the impact of quantum channel noise and has significant potential application in future research of quantum knowledge graphs and recommendation systems.

arXiv:2501.07986•IEEE Transactions on Emerging Topics in Computational Intelligence•Sep 8, 2025•5 citations

YOĞUN MADDE İÇİNDE ZAMAN YAYILIMI İÇİN KUANTUM GRAFİK SİNİR AĞLARI

Kaan Yurtseven

Quantum Graph Neural Networks (QGNN) are a new class of quantum neural network ansatz which are tailored to represent quantum processes which have a graph structure. They have application in simulating Hamiltonian dynamics of quantum systems. The topology of the graph plays an important role, e.g. in inferring stability of steady states. They also manage to reproduce transmission fluctuations and can be generalized to the nonlinear domain. In this work, we adapt QGNN for simulating electronic dynamics in condensed matter systems. We are particulary interested in Fermi-Hubbard model in line with this, we investigated time evolution and scaling of Majonara Hubbard Model. We employ Quantum Autoencoder architecture to be able to simulate fermionic wavefunction in latent space using compressed wavefunctions propagation in time.

•Oct 8, 2024•0 citations

On the Design of Quantum Graph Convolutional Neural Network in the NISQ-Era and Beyond

Zhirui Hu, Jinyang Li, Zhenyu Pan +6 more

The rapid growth in the size of Graph Convolutional Neural Networks (GCNs) encounters both computational- and memory-wall on classical computing platforms (e.g., CPU, GPU, FPGA, etc.). Quantum computing, on the other hand, provides extremely high parallelism for computation. Although quantum neural networks have been recently studied, the research on quantum graph neural networks is still in its infancy. The key challenge here is how to integrate both the graph topology information and the learning ability of GCNs into quantum circuits. In this work, we leverage the Givens rotations and its quantum implementation to encode graph information; in addition, we employ the widely used variational quantum circuit to bring the learnable parameters. On top of these, we present a full-quantum design of Graph Convolutional Neural Networks, namely "QuGCN", for semi-supervised learning on graph-structured data. Experiment results show our design is competitive with classical GCNs in terms of node classification accuracy on Cora sub-dataset. More importantly, we show the potential advantages that can be achieved by the proposed quantum GCN design when the number of features grows.

IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD)•Oct 1, 2022•28 citations

Inductive Graph Representation Learning with Quantum Graph Neural Networks

Arthur Mendonça Faria, Ignacio Fernández Graña, Savvas Varsamopoulos

Graph Neural Networks (QGNNs) offer a promising approach to combining quantum computing with graph-structured data processing. While classical Graph Neural Networks (GNNs) are scalable and robust, existing QGNNs often lack flexibility due to graph-specific quantum circuit designs, limiting their applicability to diverse real-world problems. To address this, we propose a versatile QGNN framework inspired by GraphSAGE, using quantum models as aggregators to generate quantum-native node embeddings. We integrate inductive representation learning techniques with parameterized quantum convolutional and pooling layers, bridging classical and quantum paradigms. The convolutional layer is flexible, allowing tailored designs for specific tasks. Benchmarked on a node regression task with the QM9 dataset, our framework, using a single minimal circuit for all aggregation steps, handles molecules with varying numbers of atoms without changing qubits or circuit architecture. While classical GNNs achieve higher training performance, our quantum approach remains competitive and often shows enhanced generalization as molecular complexity increases. We also observe faster learning in early training epochs. To mitigate trainability limitations of a single-circuit setup, we extend the framework with multiple quantum aggregators on QM9. Assigning distinct circuits to each hop substantially improves training performance across all cases. Additionally, we numerically demonstrate the absence of barren plateaus as qubit numbers increase, suggesting that the proposed model remains trainable to larger, more complex graph-based problems.

arXiv:2503.24111•Mar 31, 2025•0 citations

Quantum Graph Convolutional Networks: Implementation and Trainability Analysis

Paul San Sebastian Sein, Theodor Iosif, Tilen G. Limbäck-Stokin +2 more

Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottlenecked by memory constraints and sparse linear-algebra workloads. Quantum computing offers an alternative set of primitives that may improve scalability for graph learning. Building on the quantum graph neural network (QGNN) framework of Liao \textit{et al.}, this work implements two representative architectures --- the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models --- and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation. We compare predictive performance and optimization behavior against classical baselines, showing that the quantum models achieve competitive performance with fewer parameters. Finally, we present a cost gradient analysis that identifies the tasks for which the models showcased are trainable. This is followed by a classical simulability study to find regimes in which the proposed circuits remain robust during training.

quant-pharXiv:2609.19983•Sep 18, 2026•0 citations
We introduce Quantum Graph Neural Networks (QGNN), a new class of quantum neural network ansatze which are tailored to represent quantum processes which have a graph structure, and are particularly suitable to be executed on distributed quantum systems over a quantum network. Along with this general class of ansatze, we introduce further specialized architectures, namely, Quantum Graph Recurrent Neural Networks (QGRNN) and Quantum Graph Convolutional Neural Networks (QGCNN). We provide four example applications of QGNNs: learning Hamiltonian dynamics of quantum systems, learning how to create multipartite entanglement in a quantum network, unsupervised learning for spectral clustering, and supervised learning for graph isomorphism classification.
Over the past decades, various neural networks have been proposed with the rapid development of the machine learning field. In particular, graph neural networks using feature-vectors assigned to nodes and edges have been attracting attention in various fields. The usefulness of graph neural networks also affected the field of quantum computing, which led to the birth of quantum graph neural networks composed of parameterized quantum circuits. The quantum graph neural networks have many possibilities as applications from the simulation perspective of quantum dynamics. Among the application models of various quantum graph neural networks, the quantum graph recurrent neural network (QGRNN) is proven to be effective in training the Ising model Hamiltonian. Thus, this paper introduces the concepts of the Ising model, variational quantum eigensolver (VQE) for preparing quantum data, and QGRNN from a software engineer's point of view.
Representing and learning from graphs is essential for developing effective machine learning models tailored to non-Euclidean data. While Graph Neural Networks (GNNs) strive to address the challenges posed by complex, high-dimensional graph data, Quantum Neural Networks (QNNs) present a compelling alternative due to their potential for quantum parallelism. However, much of the current QNN research tends to overlook the vital connection between quantum state encoding and graph structures, which limits the full exploitation of quantum computational advantages. To address these challenges, this paper introduces a quantum graph Hamiltonian neural network (QGHNN) to enhance graph representation and learning on noisy intermediate-scale quantum computers. Concretely, a quantum graph Hamiltonian learning method (QGHL) is first created by mapping graphs to the Hamiltonian of the topological quantum system. Then, QGHNN based on QGHL is presented, which trains parameters by minimizing the loss function and uses the gradient descent method to learn the graph. Experiments on the PennyLane quantum platform reveal that QGHNN outperforms all assessment metrics, achieving the lowest mean squared error of0.004and the maximum cosine similarity of99.8%, which shows that QGHNN not only excels in representing and learning graph information, but it also has high robustness ability. QGHNN can reduce the impact of quantum channel noise and has significant potential application in future research of quantum knowledge graphs and recommendation systems.
Quantum Graph Neural Networks (QGNN) are a new class of quantum neural network ansatz which are tailored to represent quantum processes which have a graph structure. They have application in simulating Hamiltonian dynamics of quantum systems. The topology of the graph plays an important role, e.g. in inferring stability of steady states. They also manage to reproduce transmission fluctuations and can be generalized to the nonlinear domain. In this work, we adapt QGNN for simulating electronic dynamics in condensed matter systems. We are particulary interested in Fermi-Hubbard model in line with this, we investigated time evolution and scaling of Majonara Hubbard Model. We employ Quantum Autoencoder architecture to be able to simulate fermionic wavefunction in latent space using compressed wavefunctions propagation in time.
The rapid growth in the size of Graph Convolutional Neural Networks (GCNs) encounters both computational- and memory-wall on classical computing platforms (e.g., CPU, GPU, FPGA, etc.). Quantum computing, on the other hand, provides extremely high parallelism for computation. Although quantum neural networks have been recently studied, the research on quantum graph neural networks is still in its infancy. The key challenge here is how to integrate both the graph topology information and the learning ability of GCNs into quantum circuits. In this work, we leverage the Givens rotations and its quantum implementation to encode graph information; in addition, we employ the widely used variational quantum circuit to bring the learnable parameters. On top of these, we present a full-quantum design of Graph Convolutional Neural Networks, namely "QuGCN", for semi-supervised learning on graph-structured data. Experiment results show our design is competitive with classical GCNs in terms of node classification accuracy on Cora sub-dataset. More importantly, we show the potential advantages that can be achieved by the proposed quantum GCN design when the number of features grows.
Graph Neural Networks (QGNNs) offer a promising approach to combining quantum computing with graph-structured data processing. While classical Graph Neural Networks (GNNs) are scalable and robust, existing QGNNs often lack flexibility due to graph-specific quantum circuit designs, limiting their applicability to diverse real-world problems. To address this, we propose a versatile QGNN framework inspired by GraphSAGE, using quantum models as aggregators to generate quantum-native node embeddings. We integrate inductive representation learning techniques with parameterized quantum convolutional and pooling layers, bridging classical and quantum paradigms. The convolutional layer is flexible, allowing tailored designs for specific tasks. Benchmarked on a node regression task with the QM9 dataset, our framework, using a single minimal circuit for all aggregation steps, handles molecules with varying numbers of atoms without changing qubits or circuit architecture. While classical GNNs achieve higher training performance, our quantum approach remains competitive and often shows enhanced generalization as molecular complexity increases. We also observe faster learning in early training epochs. To mitigate trainability limitations of a single-circuit setup, we extend the framework with multiple quantum aggregators on QM9. Assigning distinct circuits to each hop substantially improves training performance across all cases. Additionally, we numerically demonstrate the absence of barren plateaus as qubit numbers increase, suggesting that the proposed model remains trainable to larger, more complex graph-based problems.
Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottlenecked by memory constraints and sparse linear-algebra workloads. Quantum computing offers an alternative set of primitives that may improve scalability for graph learning. Building on the quantum graph neural network (QGNN) framework of Liao \textit{et al.}, this work implements two representative architectures --- the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models --- and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation. We compare predictive performance and optimization behavior against classical baselines, showing that the quantum models achieve competitive performance with fewer parameters. Finally, we present a cost gradient analysis that identifies the tasks for which the models showcased are trainable. This is followed by a classical simulability study to find regimes in which the proposed circuits remain robust during training.