EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid quantum-classical generative adversarial networks with transfer learning

Asma Al-Othni, Saif Al-Kuwari, Mohammad Mahdi Nasiri Fatmehsari, Kamila Zaman, Ebrahim Ardeshir-Larijani

Quantum Machine Intelligence · 2026-06 · 8 (1)

DOI: 10.1007/s42484-026-00389-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Quantum Machine Intelligence, online erschienen am 27.04.2026. Verfasst von Asma Al-Othni und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hamad bin Khalifa University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images. However, critical questions remain unanswered regarding how quantum principles might best enhance their representational and computational capacity. In this paper, we investigate hybrid quantum-classical GAN architectures supplemented by transfer learning to systematically examine whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over a fully classical baseline. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, produce images with higher quality and achieve more favorable quantitative metrics compared to their fully classical counterparts. In particular, placing the quantum block in the generator appears to accelerate the early emergence of visual structure, whereas placing it in the discriminator slows early visual convergence but improves the final quantitative quality metric. Incorporating quantum blocks into both networks yields the strongest overall performance. Moreover, the model sustains comparable performance even when the dataset size is reduced. Overall, the results underscore that carefully integrating quantum computing with classical adversarial training and pretrained feature extraction can enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.

Förderung

  • Hamad bin Khalifa University

Zitieren

APA

Al-Othni, A., Al-Kuwari, S., Fatmehsari, M. M. N., Zaman, K., & Ardeshir-Larijani, E. (2026). Hybrid quantum-classical generative adversarial networks with transfer learning. Quantum Machine Intelligence, 8(1). https://doi.org/10.1007/s42484-026-00389-2

Vancouver

Al-Othni A, Al-Kuwari S, Fatmehsari MMN, Zaman K, Ardeshir-Larijani E. Hybrid quantum-classical generative adversarial networks with transfer learning. Quantum Machine Intelligence. 2026;8(1). doi:10.1007/s42484-026-00389-2

BibTeX
@article{AlOthni2026,
  author = {Al-Othni, Asma and Al-Kuwari, Saif and Fatmehsari, Mohammad Mahdi Nasiri and Zaman, Kamila and Ardeshir-Larijani, Ebrahim},
  title = {Hybrid quantum-classical generative adversarial networks with transfer learning},
  journal = {Quantum Machine Intelligence},
  year = {2026},
  volume = {8},
  number = {1},
  doi = {10.1007/s42484-026-00389-2}
}
Kostenlos starten →