Home > Research > Publications & Outputs > Enable Quantum Graph Neural Networks on a Singl...

Research

Associated organisational unit

Electronic data

  • Graph_TAI_Final

    Accepted author manuscript, 1.12 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk

Research output: Contribution to Journal/Magazine › Journal article › peer-review

E-pub ahead of print

Standard

Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk. / Zhu, Yijie; Jiang, Richard; Ni, Qiang et al.
In: IEEE Transactions on Artificial Intelligence, 28.07.2025.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Zhu, Y, Jiang, R, Ni, Q & Bouridane, A 2025, 'Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk', IEEE Transactions on Artificial Intelligence. https://doi.org/10.1109/tai.2025.3592896

APA

Zhu, Y., Jiang, R., Ni, Q., & Bouridane, A. (2025). Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk. IEEE Transactions on Artificial Intelligence. Advance online publication. https://doi.org/10.1109/tai.2025.3592896

Vancouver

Zhu Y, Jiang R, Ni Q, Bouridane A. Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk. IEEE Transactions on Artificial Intelligence. 2025 Jul 28. Epub 2025 Jul 28. doi: 10.1109/tai.2025.3592896

Author

Zhu, Yijie ; Jiang, Richard ; Ni, Qiang et al. / Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk. In: IEEE Transactions on Artificial Intelligence. 2025.

Bibtex

@article{39f41199681549f9a5628e1ed0f219ec,
title = "Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk",
abstract = "Quantum computing holds significant potential for advancing machine learning, particularly in handling complex graph-structured data. This paper introduces Single-Qubit Quantum Graph Neural Networks (sQGNNs), a novel model that integrates quantum networks with quantum walk operations to improve generalization in graph learning tasks. By leveraging quantum walks, we demonstrated sQGNNs capture complex relational patterns and enhance network expressiveness beyond classical methods. Our results proved that quantum encoding efficiently represents high-dimensional graph data, preserving dependencies and optimizing memory use. Across benchmark datasets, sQGNNs demonstrate superior generalization and robustness against overfitting, achieving higher accuracy with reduced computational cost. Our results underscore sQGNNs{\textquoteright} promise for scalable, quantum-enhanced graph learning, establishing a foundation for future quantum-assisted machine learning applications.",
author = "Yijie Zhu and Richard Jiang and Qiang Ni and Ahmed Bouridane",
year = "2025",
month = jul,
day = "28",
doi = "10.1109/tai.2025.3592896",
language = "English",
journal = "IEEE Transactions on Artificial Intelligence",
issn = "2691-4581",
publisher = "IEEE",

}

RIS

TY - JOUR

T1 - Enable Quantum Graph Neural Networks on a Single Qubit with Quantum Walk

AU - Zhu, Yijie

AU - Jiang, Richard

AU - Ni, Qiang

AU - Bouridane, Ahmed

PY - 2025/7/28

Y1 - 2025/7/28

N2 - Quantum computing holds significant potential for advancing machine learning, particularly in handling complex graph-structured data. This paper introduces Single-Qubit Quantum Graph Neural Networks (sQGNNs), a novel model that integrates quantum networks with quantum walk operations to improve generalization in graph learning tasks. By leveraging quantum walks, we demonstrated sQGNNs capture complex relational patterns and enhance network expressiveness beyond classical methods. Our results proved that quantum encoding efficiently represents high-dimensional graph data, preserving dependencies and optimizing memory use. Across benchmark datasets, sQGNNs demonstrate superior generalization and robustness against overfitting, achieving higher accuracy with reduced computational cost. Our results underscore sQGNNs’ promise for scalable, quantum-enhanced graph learning, establishing a foundation for future quantum-assisted machine learning applications.

AB - Quantum computing holds significant potential for advancing machine learning, particularly in handling complex graph-structured data. This paper introduces Single-Qubit Quantum Graph Neural Networks (sQGNNs), a novel model that integrates quantum networks with quantum walk operations to improve generalization in graph learning tasks. By leveraging quantum walks, we demonstrated sQGNNs capture complex relational patterns and enhance network expressiveness beyond classical methods. Our results proved that quantum encoding efficiently represents high-dimensional graph data, preserving dependencies and optimizing memory use. Across benchmark datasets, sQGNNs demonstrate superior generalization and robustness against overfitting, achieving higher accuracy with reduced computational cost. Our results underscore sQGNNs’ promise for scalable, quantum-enhanced graph learning, establishing a foundation for future quantum-assisted machine learning applications.

U2 - 10.1109/tai.2025.3592896

DO - 10.1109/tai.2025.3592896

M3 - Journal article

JO - IEEE Transactions on Artificial Intelligence

JF - IEEE Transactions on Artificial Intelligence

SN - 2691-4581

ER -