QGAN-based data augmentation for hybrid quantum–classical neural networks

IF 4.6 2区 物理与天体物理 Q1 PHYSICS, MULTIDISCIPLINARY
Run-Ze He , Jun-Jian Su , Su-Juan Qin , Zheng-Ping Jin , Fei Gao
{"title":"QGAN-based data augmentation for hybrid quantum–classical neural networks","authors":"Run-Ze He ,&nbsp;Jun-Jian Su ,&nbsp;Su-Juan Qin ,&nbsp;Zheng-Ping Jin ,&nbsp;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}
引用次数: 0

Abstract

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.

Abstract Image

基于qgan的混合量子经典神经网络数据增强
混合量子-经典神经网络(HQNNs)在复杂特征空间中具有比经典神经网络更快的训练收敛和更高的精度的潜力。然而,由于在生成量子数据和数据稀缺性恶化方面的挑战,量子机器学习的数据增强尚未得到充分探索。为了解决这个问题,我们将量子生成对抗网络(qgan)与hqnn集成在一起,并提出了两种策略:一种是改进数据处理和分类的通用方法,另一种是基于hqnn在特定类别上的性能生成样本的定制策略。在MNIST数据集上的仿真实验表明,QGAN优于传统的数据增强方法(随机旋转、平移、对比度调整)和经典gan。与深度卷积GAN相比,QGAN在可训练参数减少50%的情况下取得了相似的性能,平衡了效率和有效性。这些结果突出了量子数据增强技术的优势,为罕见疾病诊断和濒危物种分类等现实应用提供了潜在的解决方案。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Chinese Journal of Physics
Chinese Journal of Physics 物理-物理:综合
CiteScore
8.50
自引率
10.00%
发文量
361
审稿时长
44 days
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.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信