Run-Ze He , Jun-Jian Su , Su-Juan Qin , Zheng-Ping Jin , Fei Gao
{"title":"基于qgan的混合量子经典神经网络数据增强","authors":"Run-Ze He , Jun-Jian Su , Su-Juan Qin , Zheng-Ping Jin , Fei Gao","doi":"10.1016/j.cjph.2025.07.017","DOIUrl":null,"url":null,"abstract":"<div><div>Hybrid Quantum–Classical Neural Networks (HQNNs) have the potential to achieve faster training convergence and higher accuracy than classical neural networks in complex feature spaces. However, data augmentation for quantum machine learning is underexplored due to challenges in generating quantum data and worsening data scarcity. To address this, we integrate Quantum Generative Adversarial Networks (QGANs) with HQNNs, and propose two strategies: a general approach to improve data processing and classification, and a customized strategy that generates samples based on HQNNs’ performance on specific classes. Simulation experiments on the MNIST dataset demonstrate that QGAN outperforms conventional data augmentation methods(random rotation, translation, contrast adjustment) and classical GANs. Compared to deep convolutional GAN, QGAN achieves similar performance with 50% fewer trainable parameters, balancing efficiency and effectiveness. These results highlight the advantages of quantum data augmentation techniques, offering potential solutions for real-world applications such as rare disease diagnosis and endangered species classification.</div></div>","PeriodicalId":10340,"journal":{"name":"Chinese Journal of Physics","volume":"97 ","pages":"Pages 1453-1463"},"PeriodicalIF":4.6000,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"QGAN-based data augmentation for hybrid quantum–classical neural networks\",\"authors\":\"Run-Ze He , Jun-Jian Su , Su-Juan Qin , Zheng-Ping Jin , Fei Gao\",\"doi\":\"10.1016/j.cjph.2025.07.017\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Hybrid Quantum–Classical Neural Networks (HQNNs) have the potential to achieve faster training convergence and higher accuracy than classical neural networks in complex feature spaces. However, data augmentation for quantum machine learning is underexplored due to challenges in generating quantum data and worsening data scarcity. To address this, we integrate Quantum Generative Adversarial Networks (QGANs) with HQNNs, and propose two strategies: a general approach to improve data processing and classification, and a customized strategy that generates samples based on HQNNs’ performance on specific classes. Simulation experiments on the MNIST dataset demonstrate that QGAN outperforms conventional data augmentation methods(random rotation, translation, contrast adjustment) and classical GANs. Compared to deep convolutional GAN, QGAN achieves similar performance with 50% fewer trainable parameters, balancing efficiency and effectiveness. These results highlight the advantages of quantum data augmentation techniques, offering potential solutions for real-world applications such as rare disease diagnosis and endangered species classification.</div></div>\",\"PeriodicalId\":10340,\"journal\":{\"name\":\"Chinese Journal of Physics\",\"volume\":\"97 \",\"pages\":\"Pages 1453-1463\"},\"PeriodicalIF\":4.6000,\"publicationDate\":\"2025-07-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Chinese Journal of Physics\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0577907325002849\",\"RegionNum\":2,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PHYSICS, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chinese Journal of Physics","FirstCategoryId":"101","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0577907325002849","RegionNum":2,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
QGAN-based data augmentation for hybrid quantum–classical neural networks
Hybrid Quantum–Classical Neural Networks (HQNNs) have the potential to achieve faster training convergence and higher accuracy than classical neural networks in complex feature spaces. However, data augmentation for quantum machine learning is underexplored due to challenges in generating quantum data and worsening data scarcity. To address this, we integrate Quantum Generative Adversarial Networks (QGANs) with HQNNs, and propose two strategies: a general approach to improve data processing and classification, and a customized strategy that generates samples based on HQNNs’ performance on specific classes. Simulation experiments on the MNIST dataset demonstrate that QGAN outperforms conventional data augmentation methods(random rotation, translation, contrast adjustment) and classical GANs. Compared to deep convolutional GAN, QGAN achieves similar performance with 50% fewer trainable parameters, balancing efficiency and effectiveness. These results highlight the advantages of quantum data augmentation techniques, offering potential solutions for real-world applications such as rare disease diagnosis and endangered species classification.
期刊介绍:
The Chinese Journal of Physics publishes important advances in various branches in physics, including statistical and biophysical physics, condensed matter physics, atomic/molecular physics, optics, particle physics and nuclear physics.
The editors welcome manuscripts on:
-General Physics: Statistical and Quantum Mechanics, etc.-
Gravitation and Astrophysics-
Elementary Particles and Fields-
Nuclear Physics-
Atomic, Molecular, and Optical Physics-
Quantum Information and Quantum Computation-
Fluid Dynamics, Nonlinear Dynamics, Chaos, and Complex Networks-
Plasma and Beam Physics-
Condensed Matter: Structure, etc.-
Condensed Matter: Electronic Properties, etc.-
Polymer, Soft Matter, Biological, and Interdisciplinary Physics.
CJP publishes regular research papers, feature articles and review papers.