一种学习多域数据联合分布的量子耦合生成对抗网络

doi:10.12305/j.issn.1001-506X.2026.03.05

摘要/Abstract

摘要：

一般量子生成对抗网络（generative adversarial network，GAN）只能处理单域数据，且受到量子比特数限制，生成质量会有很大程度下降。对此，提出一种学习多域数据联合分布的量子耦合GAN（quantum coupled GAN，QCoGAN）。QCoGAN通过结合量子计算的并行计算能力和经典GAN的学习能力，对量子GAN结构进行耦合优化，相较于普通GAN可以捕捉到更多图像细节，通过施加量子参数层之间的权重共享约束，有效控制了网络容量，提升了训练效率。将量子GAN用于领域适应问题，将QCoGAN应用于多个手写体数据集的联合分布学习任务，证明了其在处理多域数据时的优越性，具有广阔的应用前景。

关键词: 量子计算, 机器学习, 生成对抗网络, 量子耦合, 多域数据

Abstract:

Ordinary quantum generative adversarial network （GAN） can only handle single domain data and are limited by the number of quantum bits, resulting in a significant decrease in generation quality. In regard to this, a quantum coupled GAN （QCoGAN） is proposed to learn the joint distribution of multi domain data. QCoGAN combines the parallel computing capability of quantum computing with the learning ability of classical GANs to couple and optimize the structure of quantum GANs. Compared with ordinary GANs, it can capture more image details. By applying weight sharing constraints between quantum parameter layers, it effectively controls the network capacity and improves training efficiency. Applying quantum GAN to domain adaptation problems and QCoGAN to joint distributed learning tasks on multiple handwritten datasets is demonstrated its superiority in handling multi domain data and has broad application prospects.

Key words: quantum computing, machine learning, generative adversarial network (GAN), quantum coupling, multi-domain data

中图分类号:

TN 929.5

吉家欣, 李汀, 李飞. 一种学习多域数据联合分布的量子耦合生成对抗网络[J]. 系统工程与电子技术, 2026, 48(3): 779-786.

Jiaxin JI, Ting LI, Fei LI. A quantum coupled generative adversarial network for learning the joint distribution of multi-domain data[J]. Systems Engineering and Electronics, 2026, 48(3): 779-786.

图/表 18

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

图17

表1

参考文献 13

14	PETERS E, CALDEIRA J, HO A, et al. Machine learning of high dimensional data on a noisy quantum processor[J]. npj Quantum Information, 2021, 7, 161. doi: 10.1038/s41534-021-00498-9
15	LIU J G, WANG L. Differentiable learning of quantum circuit born machines[J]. Physical Review A, 2018, 98 (6): 062324. doi: 10.1103/PhysRevA.98.062324
16	ZHU D W, LINKE N M, BENEDETTI M, et al. Training of quantum circuits on a hybrid quantum computer[J]. Science Advances, 2019, 5 (10): eaaw9918. doi: 10.1126/sciadv.aaw9918
17	SOMBILLO N I. Simulation of quantum algorithm using modified qubit rotation[C]//Proc. of the 11th International Conference on Mathematical Modeling in Physical Sciences, 2023.
18	YU C H. Experimental implementation of quantum algorithm for association rules mining[J]. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2022, 12 (3): 676- 684. doi: 10.1109/JETCAS.2022.3201097
19	LLOYD S, WEEDBROOK C, Quantum generative adversarial learning[J]. Physical Review Letter, 2018, 121: 040502.
20	HUANG H L, DU Y X, GONG M, et al, Experimental quantum generative adversarial networks for image generation[J]. Physical Review Applied, 2021, 16: 024051.
21	GOODFELLOW I, BENGIO Y, COURVILLE A. Deep learning[M]. Cambridge: MIT Press, 2018.
22	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60 (6): 84- 90. doi: 10.1145/3065386
23	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770−778.
24	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proc. of the 31st International Conference on Neural Information Processing Systems, 2017: 5998−6008.
25	SRIVASTAVA N, SALAKHUTDINOV R R. Multimodal learning with deep boltzmann machines[J]. The Journal of Machine Learning Research, 2014, 15 (1): 2949- 2980.
26	MENSA S, SAHIN E, TACCHINO F, et al. Quantum machine learning framework for virtual screening in drug discovery: a prospective quantum advantage[J]. Machine Learning: Science and Technology, 2023, 4 (1): 015023. doi: 10.1088/2632-2153/acb900
27	WANG S L, ZHANG L, LIANG Y, et al. Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2012: 16−21.
28	NGIAM J, KHOSLA A, KIM M, et al. Multimodal deep learning[C]//Proc. of the 28th International Conference on International Conference on Machine Learning, 2011: 689−696.
29	YANG J C, WRIGHT J, HUANG T S, et al. Image super-resolution via sparse representation[J]. IEEE Trans. on Image Processing, 2010, 19 (11): 2861- 2873. doi: 10.1109/TIP.2010.2050625
30	LIU M Y, TUZEL O. Coupled generative adversarial networks[C]//Proc. of the 29th International Conference on Neural Information Processing Systems, 2016: 469−477.
1	SARMA S D, DENG D L, DUAN L M. Machine learning meets quantum physics[J]. Physics Today, 2019, 72 (3): 48- 54. doi: 10.1063/PT.3.4164
2	JORDAN M, MITCHELL T. Machine learning: trends, perspectives, and prospects[J]. Science, 2015, 349 (6245): 255- 260.
3	LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521, 436- 444. doi: 10.1038/nature14539
4	王鹏, 王方. 量子视角下的智能优化算法综述[J]. 电子科技大学学报, 2022, 51 (1): 2- 15. doi: 10.12178/1001-0548.2021345
	WANG P, WANG F. Overview of intelligent optimization algorithms from the perspective of quantum[J]. Journal of University of Electronic Science and Technology of China, 2022, 51 (1): 2- 15. doi: 10.12178/1001-0548.2021345
5	SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of go with deep neural networks and tree search[J]. Nature, 2016, 529, 484- 489. doi: 10.1038/nature16961
6	乔笑斐, 路昊明, 高策. 量子信息革命引领未来科技革命[J]. 科技导报, 2023, 41 (3): 81- 88.
	QIAO X F, LU H M, GAO C. Quantum information revolution leads the future revolution of science and technology[J]. Science & Technology Review, 2023, 41 (3): 81- 88.
7	CARLEO G, TROYER M. Solving the quantum many-body problem with artificial neural networks[J]. Science, 2017, 355, 602- 606. doi: 10.1126/science.aag2302
8	孙太平, 吴玉椿, 郭国平. 量子生成模型[J]. 物理学报, 2021, 70 (14): 140304. doi: 10.7498/aps.70.20210930
	SUN T P, WU Y C, GUO G P. Quantum generative models for data generation[J]. Acta Physica Sinica, 2021, 70 (14): 140304. doi: 10.7498/aps.70.20210930
9	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proc. of the 28th International Conference on Neural Information Processing Systems, 2014: 2672−2680.
10	DALLAIRE-DEMERS P, KILLORAN N. Quantum generative adversarial networks[J]. Physical Review A, 2018, 98, 012324. doi: 10.1103/PhysRevA.98.012324
11	陆思聪, 郑昱, 王晓霆, 等. 量子机器学习[J]. 控制理论与应用, 2017, 34 (11): 1429- 1436.
	LU S C, ZHENG Y, WANG X T, et al. Quantum machine learning[J]. Control Theory & Applications, 2017, 34 (11): 1429- 1436.
12	YANO H, SUZUKI Y, ITOH K M, et al. Efficient discrete feature encoding for variational quantum classifier[J]. IEEE Trans. on Quantum Engineering, 2021, 2, 3103214. doi: 10.1109/qce49297.2020.00012
13	SCHULD M, BOCHAROV A, SVOREK M, et al. Circuit-centric quantum classifiers[J]. Physical Review A, 2020, 101 (3): 032308. doi: 10.1103/PhysRevA.101.032308

数据库	[26]	[27]	[28]	[29]	QCoGAN
MNIST-USPS	0.408	0.467	0.478	0.607	0.756
USPS-MNIST	0.274	0.355	0.631	0.673	0.825
平均值	0.341	0.411	0.554	0.640	0.790

[1]	张振兴, 杨任农, 李永林, 左家亮, 胡利平, 陈双艳. 基于双重注意力生成对抗网络的文本到图像生成[J]. 系统工程与电子技术, 2026, 48(1): 34-43.
[2]	张兰, 张彪, 梁天一, 朱辉杰. 面向电磁信息智能控制的生成对抗网络研究进展[J]. 系统工程与电子技术, 2025, 47(3): 730-744.
[3]	贾钰嘉, 张思乾, 唐涛, 匡纲要. 强化散射特征的机载SAR实传图像盲超分辨重建[J]. 系统工程与电子技术, 2025, 47(3): 753-767.
[4]	潘晨辉, 鲜勇, 马培洋, 倪晚成, 赵晓楠, 李少朋. 兵棋推演态势认知的态势数学表达方法[J]. 系统工程与电子技术, 2025, 47(3): 883-892.
[5]	刘嘉俊, 鲁祖坤, 肖伟, 李宗楠, 刘哲. 卫星导航接收机射频前端非线性失真建模综述[J]. 系统工程与电子技术, 2025, 47(3): 938-950.
[6]	张文中, 侯长波, 赵鹏旗, 刘思成. 基于GCN的无人机目标航迹关联[J]. 系统工程与电子技术, 2025, 47(12): 4005-4011.
[7]	唐曦, 李文海, 唐贞豪, 李睿峰, 李根. 基于DBSCAN和CGAN的不平衡数据过采样方法[J]. 系统工程与电子技术, 2025, 47(11): 3739-3753.
[8]	薛丽莎, 葛瑞星, 朱宇轩, 鲍雁飞. 基于SABEGAN的通信干扰信号生成与效能分析[J]. 系统工程与电子技术, 2024, 46(6): 2155-2163.
[9]	汤寓麟, 王黎明, 余德荧, 李厚朴, 刘敏, 张卫东. 基于CSLS-CycleGAN的侧扫声纳水下目标图像样本扩增法[J]. 系统工程与电子技术, 2024, 46(5): 1514-1524.
[10]	王希, 任惠, 王威, 张嘉怡, 赵洪山. URLLC场景下信道可靠连通度预测[J]. 系统工程与电子技术, 2024, 46(5): 1810-1819.
[11]	马兰, 孟诗君, 吴志军. 基于BERT与生成对抗的民航陆空通话意图挖掘[J]. 系统工程与电子技术, 2024, 46(2): 740-750.
[12]	季然, 肖茂森, 李硕, 刘宇, 罗湛仪, 程嘉维. 基于机器学习的MRTD客观测试方法研究[J]. 系统工程与电子技术, 2024, 46(10): 3265-3270.
[13]	刘文波, 姚翼荣, 张弓, 胡文. 超维计算概念、应用及研究进展[J]. 系统工程与电子技术, 2023, 45(7): 1938-1956.
[14]	王湖升, 陈伯孝, 叶倾知. 基于箔条干扰实测数据的对抗方法研究[J]. 系统工程与电子技术, 2023, 45(7): 2010-2021.
[15]	庞世燕, 郝京京, 邢立宁, 谭旭. 融合域自适应和弱监督策略的遥感影像建筑物提取算法[J]. 系统工程与电子技术, 2023, 45(6): 1616-1623.