EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

QKSAN: A Quantum Kernel Self-Attention Network

Ren-Xin Zhao, Jinjing Shi, Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10184-10195

DOI: 10.1109/tpami.2024.3434974 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Ren-Xin Zhao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 77-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation of China, Science Fund for Distinguished Young Scholars of Hunan Province, Special Foundation for Distinguished Young Scientists of Changsha.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Self-Attention Mechanism (SAM) excels at distilling important information from the interior of data to improve the computational efficiency of models. Nevertheless, many Quantum Machine Learning (QML) models lack the ability to distinguish the intrinsic connections of information like SAM, which limits their effectiveness on massive high-dimensional quantum data. To tackle the above issue, a Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. Further, a Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques to release half of quantum resources by mid-circuit measurement, thereby bolstering both feasibility and adaptability. Simultaneously, the Quantum Kernel Self-Attention Score (QKSAS) with an exponentially large characterization space is spawned to accommodate more information and determine the measurement conditions. Eventually, four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST, where the QKSAS tests and correlation assessments between noise immunity and learning ability are executed on the best-performing sub-model. The paramount experimental finding is that the QKSAN subclasses possess the potential learning advantage of acquiring impressive accuracies exceeding 98.05% with far fewer parameters than classical machine learning models. Predictably, QKSAN lays the foundation for future quantum computers to perform machine learning on massive amounts of data while driving advances in areas such as quantum computer vision.

Förderung

  • National Natural Science Foundation of China
  • Science Fund for Distinguished Young Scholars of Hunan Province
  • Special Foundation for Distinguished Young Scientists of Changsha
  • Research Fund of Guangxi Key Lab of Multi-source Information Mining & Security

Zitieren

APA

Zhao, R. X., Shi, J., & Li, X. (2024). QKSAN: A Quantum Kernel Self-Attention Network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10184-10195. https://doi.org/10.1109/tpami.2024.3434974

Vancouver

Zhao RX, Shi J, Li X. QKSAN: A Quantum Kernel Self-Attention Network. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10184-10195. doi:10.1109/tpami.2024.3434974

BibTeX
@article{Zhao2024,
  author = {Zhao, Ren-Xin and Shi, Jinjing and Li, Xuelong},
  title = {QKSAN: A Quantum Kernel Self-Attention Network},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {10184--10195},
  doi = {10.1109/tpami.2024.3434974}
}
Kostenlos starten →