{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:02:33Z","timestamp":1771956153167,"version":"3.50.1"},"reference-count":59,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62171470"],"award-info":[{"award-number":["62171470"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100006407","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"crossref","award":["232300421240"],"award-info":[{"award-number":["232300421240"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Henan Province Central Plains Science and Technology Innovation Leading Talent Project","award":["234200510019"],"award-info":[{"award-number":["234200510019"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Quantum generative adversarial networks (QGANs) have demonstrated strong capabilities in tasks like synthetic data generation and detecting anomalies. Recent developments have increasingly integrated traditional machine learning techniques to boost the performance of QGANs. Motivated by this progress, we propose an innovative QGAN architecture that incorporates a classical learning component and employs a dual-generator design. Our approach improves upon the traditional hybrid quantum\u2013classical GAN structure and introduces a redesigned loss function tailored for the new model. Experiments on multiple datasets indicate that our method surpasses previous techniques in image generation quality, achieving a 1.38% average reduction in Fr\u00e9chet inception distance scores compared to the current state-of-the-art, and improvements of 6.52%, 0.36%, and 0.38% in structural similarity index, cosine similarity, and peak signal-to-noise ratio metrics, respectively. Additionally, our architecture supports the generation of larger images (up to <jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                           <mml:mn>78<\/mml:mn>\n                           <mml:mstyle scriptlevel=\"0\"\/>\n                           <mml:mo>\u00d7<\/mml:mo>\n                           <mml:mstyle scriptlevel=\"0\"\/>\n                           <mml:mn>78<\/mml:mn>\n                        <\/mml:mrow>\n                     <\/mml:math>\n                  <\/jats:inline-formula>), as verified on the CelebA dataset. Simulations conducted in noisy conditions further confirm the robustness and effectiveness of both the proposed architecture and loss function.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae0bf7","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T22:58:15Z","timestamp":1758841095000},"page":"045002","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Quantum generative adversarial networks with dual generators"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9093-0142","authenticated-orcid":true,"given":"Quangong","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1335-3457","authenticated-orcid":false,"given":"Chaolong","family":"Hao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-4325","authenticated-orcid":false,"given":"NianWen","family":"Si","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9917-7794","authenticated-orcid":false,"given":"Dan","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"mlstae0bf7bib1","article-title":"Latent style-based quantum gan for high-quality image generation","author":"Chang","year":"2024","type":"preprint"},{"key":"mlstae0bf7bib2","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.012324","type":"journal-article","article-title":"Quantum generative adversarial networks","volume":"98","author":"Dallaire-Demers","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstae0bf7bib3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TQE.2021.3104804","type":"journal-article","article-title":"Quantum generative models for small molecule drug discovery","volume":"2","author":"Li","year":"2021","journal-title":"IEEE Trans. Quantum Eng."},{"key":"mlstae0bf7bib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TQE.2024.3414264","type":"journal-article","article-title":"Hybrid quantum cycle generative adversarial network for small molecule generation","volume":"5","author":"Anoshin","year":"2024","journal-title":"IEEE Trans. Quantum Eng."},{"key":"mlstae0bf7bib5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.16.024051","type":"journal-article","article-title":"Experimental quantum generative adversarial networks for image generation","volume":"16","author":"Huang","year":"2021","journal-title":"Phys. Rev. Appl."},{"key":"mlstae0bf7bib6","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ac0d4d","type":"journal-article","article-title":"Anomaly detection with variational quantum generative adversarial networks","volume":"6","author":"Herr","year":"2020","journal-title":"Quantum Sci. Technol."},{"key":"mlstae0bf7bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TQE.2023.3319319","type":"journal-article","article-title":"Hybrid quantum\u2014classical generative adversarial network for high-resolution image generation","volume":"4","author":"Tsang","year":"2023","journal-title":"IEEE Trans. Quantum Eng."},{"key":"mlstae0bf7bib8","first-page":"pp 1","type":"conference-proceedings","article-title":"IQGAN: robust quantum generative adversarial network for image synthesis on nisq devices","author":"Chu","year":"2023"},{"key":"mlstae0bf7bib9","first-page":"pp 7007","type":"conference-proceedings","article-title":"MosaiQ: quantum generative adversarial networks for image generation on nisq computers","author":"Silver","year":"2023"},{"key":"mlstae0bf7bib10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1140\/epjqt\/s40507-024-00304-3","type":"journal-article","article-title":"Quantum adversarial generation of high-resolution images","volume":"12","author":"Ma","year":"2025","journal-title":"EPJ Quantum Technol."},{"key":"mlstae0bf7bib11","doi-asserted-by":"publisher","DOI":"10.1002\/qute.202300401","type":"journal-article","article-title":"Quantum-noise-driven generative diffusion models","author":"Parigi","year":"2024","journal-title":"Adv. Quantum Technol."},{"key":"mlstae0bf7bib12","doi-asserted-by":"crossref","DOI":"10.1109\/QSW62656.2024.00023","type":"other","article-title":"Quantum denoising diffusion models","author":"K\u00f6lle","year":"2024"},{"key":"mlstae0bf7bib13","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-3688288\/v1","type":"preprint","article-title":"Quantum diffusion models","author":"Cacioppo","year":"2023"},{"key":"mlstae0bf7bib14","article-title":"Quantum generative diffusion model: A fully quantum-mechanical model for generating quantum state ensemble","author":"Chen","year":"2024","type":"preprint"},{"key":"mlstae0bf7bib15","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1007\/s13218-024-00858-5","type":"journal-article","article-title":"Quantum hybrid diffusion models for image synthesis","volume":"38","author":"De Falco","year":"2024","journal-title":"KI-K\u00fcnstliche Intelligenz"},{"key":"mlstae0bf7bib16","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.109.032623","type":"journal-article","article-title":"Quantum circuit autoencoder","volume":"109","author":"Wu","year":"2024","journal-title":"Phys. Rev. A"},{"key":"mlstae0bf7bib17","first-page":"pp 1","type":"conference-proceedings","article-title":"Efficient data loading with quantum autoencoder","author":"Wu","year":"2023"},{"key":"mlstae0bf7bib18","first-page":"pp 52","type":"conference-proceedings","article-title":"Hybrid quantum variational autoencoders for representation learning","author":"Rivas","year":"2021"},{"key":"mlstae0bf7bib19","first-page":"pp 468","type":"conference-proceedings","article-title":"Hybrid quantum-classical autoencoders for end-to-end radio communication","author":"Tabi","year":"2022"},{"key":"mlstae0bf7bib20","doi-asserted-by":"publisher","first-page":"12321","DOI":"10.1109\/TPAMI.2023.3272029","type":"journal-article","article-title":"Recent advances for quantum neural networks in generative learning","volume":"45","author":"Tian","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstae0bf7bib21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/MIS.2022.3168356","type":"journal-article","article-title":"Vgan: generalizing mse gan and wgan-gp for robot fault diagnosis","volume":"37","author":"Pu","year":"2022","journal-title":"IEEE Intell. Syst."},{"key":"mlstae0bf7bib22","first-page":"pp 105","type":"conference-proceedings","article-title":"Photo-realistic single image super-resolution using a generative adversarial network","author":"Ledig","year":"2017"},{"key":"mlstae0bf7bib23","first-page":"pp 185","type":"conference-proceedings","article-title":"To learn image super-resolution, use a gan to learn how to do image degradation first","author":"Bulat","year":"2018"},{"key":"mlstae0bf7bib24","first-page":"pp 8513","type":"conference-proceedings","article-title":"Multi-agent diverse generative adversarial networks","author":"Ghosh","year":"2018"},{"key":"mlstae0bf7bib25","first-page":"pp 2672","type":"conference-proceedings","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014"},{"key":"mlstae0bf7bib26","article-title":"Alias-free generative adversarial networks","author":"Karras","year":"2021","type":"conference-proceedings"},{"key":"mlstae0bf7bib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105382","type":"journal-article","article-title":"Generative adversarial networks in medical image augmentation: a review","volume":"144","author":"Chen","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"mlstae0bf7bib28","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10462-023-10624-y","type":"journal-article","article-title":"A survey on training challenges in generative adversarial networks for biomedical image analysis","volume":"57","author":"Saad","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"mlstae0bf7bib29","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3446374","type":"journal-article","article-title":"Generative adversarial networks (gans): challenges, solutions and future directions","volume":"54","author":"Saxena","year":"2021","journal-title":"ACM Comput. Surv."},{"key":"mlstae0bf7bib30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103329","type":"journal-article","article-title":"Pros and cons of gan evaluation measures: new developments","volume":"215","author":"Borji","year":"2022","journal-title":"Comput. Vis. Image Underst."},{"key":"mlstae0bf7bib31","doi-asserted-by":"crossref","DOI":"10.5121\/csit.2024.140208","type":"preprint","article-title":"Reviewing fid and sid metrics on generative adversarial networks","author":"de Deijn","year":"2024"},{"key":"mlstae0bf7bib32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.121.040502","type":"journal-article","article-title":"Quantum generative adversarial learning","volume":"121","author":"Lloyd","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstae0bf7bib33","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1038\/s41534-019-0223-2","type":"journal-article","article-title":"Quantum generative adversarial networks for learning and loading random distributions","volume":"5","author":"Zoufal","year":"2019","journal-title":"npj Quantum Inf."},{"key":"mlstae0bf7bib34","doi-asserted-by":"publisher","first-page":"2631","DOI":"10.1038\/s41467-021-22539-9","type":"journal-article","article-title":"Power of data in quantum machine learning","volume":"12","author":"Huang","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstae0bf7bib35","doi-asserted-by":"publisher","first-page":"eaav2761","DOI":"10.1126\/sciadv.aav2761","type":"journal-article","article-title":"Quantum generative adversarial learning in a superconducting quantum circuit","volume":"5","author":"Hu","year":"2019","journal-title":"Sci. Adv."},{"key":"mlstae0bf7bib36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.103.032430","type":"journal-article","article-title":"Effect of data encoding on the expressive power of variational quantum-machine-learning models","volume":"103","author":"Schuld","year":"2021","journal-title":"Phys. Rev. A"},{"key":"mlstae0bf7bib37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033125","type":"journal-article","article-title":"Expressive power of parametrized quantum circuits","volume":"2","author":"Du","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstae0bf7bib38","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ab4eb5","type":"journal-article","article-title":"Parameterized quantum circuits as machine learning models","volume":"4","author":"Benedetti","year":"2019","journal-title":"Quantum Sci. Technol."},{"key":"mlstae0bf7bib39","article-title":"Quantum embeddings for machine learning","author":"Lloyd","year":"2020","type":"preprint"},{"key":"mlstae0bf7bib40","first-page":"pp 214","type":"conference-proceedings","article-title":"Wasserstein generative adversarial networks","author":"Arjovsky","year":"2017"},{"key":"mlstae0bf7bib41","first-page":"pp 5769","type":"conference-proceedings","article-title":"Improved training of wasserstein gans","author":"Gulrajani","year":"2017"},{"key":"mlstae0bf7bib42","article-title":"MGAN: training generative adversarial nets with multiple generators","author":"Hoang","year":"2018","type":"conference-proceedings"},{"key":"mlstae0bf7bib43","article-title":"Unrolled generative adversarial networks","author":"Metz","year":"2017","type":"conference-proceedings"},{"key":"mlstae0bf7bib44","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1038\/nature23879","type":"journal-article","article-title":"Hardware-efficient variational quantum eigensolver for small molecules and quantum magnets","volume":"549","author":"Kandala","year":"2017","journal-title":"Nature"},{"key":"mlstae0bf7bib45","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1038\/s41467-018-07090-4","type":"journal-article","article-title":"Barren plateaus in quantum neural network training landscapes","volume":"9","author":"McClean","year":"2018","journal-title":"Nat. Commun."},{"key":"mlstae0bf7bib46","first-page":"pp 609","type":"conference-proceedings","article-title":"Quantum wasserstein gans","author":"Chakrabarti","year":"2019"},{"key":"mlstae0bf7bib47","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","type":"journal-article","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"mlstae0bf7bib48","article-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","type":"preprint"},{"key":"mlstae0bf7bib49","article-title":"Emnist: an extension of mnist to handwritten letters","author":"Cohen","year":"2017","type":"other"},{"key":"mlstae0bf7bib50","doi-asserted-by":"publisher","first-page":"3730","DOI":"10.1109\/ICCV.2015.425","type":"conference-proceedings","article-title":"Deep learning face attributes in the wild","author":"Liu","year":"2015"},{"key":"mlstae0bf7bib51","first-page":"pp 6629","type":"conference-proceedings","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017"},{"key":"mlstae0bf7bib52","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","type":"journal-article","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"mlstae0bf7bib53","doi-asserted-by":"publisher","first-page":"9967","DOI":"10.1038\/s41598-018-28270-8","type":"journal-article","article-title":"A cosine similarity algorithm method for fast and accurate monitoring of dynamic droplet generation processes","volume":"8","author":"Zhu","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstae0bf7bib54","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","type":"preprint"},{"key":"mlstae0bf7bib55","article-title":"PennyLane: automatic differentiation of hybrid quantum-classical computations","author":"Bergholm","year":"2022","type":"preprint"},{"key":"mlstae0bf7bib56","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.3.023153","type":"journal-article","article-title":"Quantum noise protects quantum classifiers against adversaries","volume":"3","author":"Du","year":"2021","journal-title":"Phys. Rev. Res."},{"key":"mlstae0bf7bib57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s42484-020-00013-x","type":"journal-article","article-title":"Quantum learning with noise and decoherence: a robust quantum neural network","volume":"2","author":"Nguyen","year":"2020","journal-title":"Quantum Mach. Intell."},{"key":"mlstae0bf7bib58","first-page":"pp 39","type":"conference-proceedings","article-title":"Towards evaluating the robustness of neural networks","author":"Carlini","year":"2017"},{"key":"mlstae0bf7bib59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/9780470479216.corpsy0524","type":"journal-article","article-title":"Mann-Whitney u test","author":"McKnight","year":"2010","journal-title":"Corsini Encyclopedia Psychol."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T06:32:17Z","timestamp":1759905137000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae0bf7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":59,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,10,8]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae0bf7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"assertion":[{"value":"Quantum generative adversarial networks with dual generators","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-07-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-25","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-10-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}