A Quantum Conditional Generative Adversarial Network Algorithm

LIU Wen-jie; ZHAO Jiao-jiao; ZHANG Ying; GE Ye-bo

doi:10.12263/DZXB.20210512

您当前的位置：

首页 >

文章列表页 >

A Quantum Conditional Generative Adversarial Network Algorithm

PAPERS | 更新时间：2025-12-08

- A Quantum Conditional Generative Adversarial Network Algorithm
- ACTA ELECTRONICA SINICA Vol. 50, Issue 7, Pages: 1586-1593(2022)
- 作者机构：
  
  1.南京信息工程大学计算机与软件学院,江苏南京 210044
  2.数字取证教育部工程研究中心,江苏南京 210044
  3.南京信息工程大学自动化学院,江苏南京 210044
- 作者简介：
- 基金信息：
- DOI：10.12263/DZXB.20210512
  CLC： TP391.41
- Received：20 April 2021，
  
  Revised：2021-12-22，
  
  Published：25 July 2022
- 稿件说明：
移动端阅览
刘文杰,赵胶胶,张颖等.一种量子条件生成对抗网络算法[J].电子学报,2022,50(07):1586-1593.

LIU Wen-jie,ZHAO Jiao-jiao,ZHANG Ying,et al.A Quantum Conditional Generative Adversarial Network Algorithm[J].ACTA ELECTRONICA SINICA,2022,50(07):1586-1593.
刘文杰,赵胶胶,张颖等.一种量子条件生成对抗网络算法[J].电子学报,2022,50(07):1586-1593. DOI： 10.12263/DZXB.20210512.

LIU Wen-jie,ZHAO Jiao-jiao,ZHANG Ying,et al.A Quantum Conditional Generative Adversarial Network Algorithm[J].ACTA ELECTRONICA SINICA,2022,50(07):1586-1593. DOI： 10.12263/DZXB.20210512.

摘要

量子生成对抗网络是量子机器学习算法领域研究热点之一，但其生成过程具有较大的随机性，不太适用于现实场景.为了解决该问题，提出了一种生成过程可控的量子条件生成对抗网络（Quantum Conditional Generative Adversarial Network，QCGAN）算法，其中条件信息采用one-hot形式进行多粒子

态编码，并通过向生成器和判别器输入条件信息达到稳定模型生成过程的目的.性能评估表明，与经典GAN、CGAN相比，本算法可生成离散数据，且将时间复杂度从

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148800&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148795&type=

8.38199997

2.87866688

降为

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148810&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148805&type=

6.77333355

2.87866688

；与带条件约束的量子生成对抗网络QuGAN相比，QCGAN消耗更少的量子资源.最后，以BAS（3，3）数据集和量子混合态生成为例，选用PennyLane平台进行仿真实验，结果表明QCGAN算法经过训练可有效收敛到Nash均衡点，进而验证了算法的实验可行性.

Abstract

Quantum generative adversarial network is one of the research hotspots in the quantum machine learning

but its generation process has a large randomness. To solve this problem

a quantum conditional generative adversarial network(QCGAN) algorithm is proposed. The one-hot method is used to encode conditional information into the multi-particle

state

and the purpose of stabilizing the model is achieved by inputting conditional information to the generator and discriminator. Compared with the classical GAN and CGAN

QCGAN can generate discrete data and reduce the time complexity from

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148820&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148815&type=

8.38199997

2.87866688

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148830&type=

http://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=39148825&type=

6.77333355

2.87866688

. In addition

our algorithm consumes less quantum resources than the conditionally constrained quantum generative adversarial network QuGAN. Finally

taking the BAS(3

3) dataset and the generation of quantum mixed states as examples

the PennyLane platform is selected for simulation experiments. The results show that QCGAN algorithm can effectively converge to the Nash equilibrium point after training

which verifies the experimental feasibility of the algorithm.

关键词

Keywords

references

GOODFELLOW I J , POUGET-ABADIE J , MIRZA M , et al . Generative adversarial nets [C]// Advances in Neural Information Processing Systems . Montreal, Canada : MIT Press , 2014 , 2672 - 2680 .

ZHU Jun-Yan , KRHENBUHL P , SHECHTMAN E , et al . Generative visual manipulation on the natural image manifold [C]// 14th European Conference on Computer Vision . Berlin : Springer , 2016 : 597 - 613 .

LEDIG C , THEIS L , HUSZAR F , et al . Photo-realistic single image super-resolution using a generative adversarial network [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu : IEEE , 2017 : 105 - 114 .

WANG C Y , XU C , WANG C H , et al . Perceptual adversarial networks for image-to-image transformation [J]. IEEE Transactions on Image Processing , 2018 , 27 ( 8 ): 4066 - 4079 .

MIRZA M , OSINDERO S . Conditional generative adversarial nets [J]. arXiv preprint , 2014 , arXiv: 1411.1784 .

MIYATO T , KOYAMA M . CGANs with projection discriminator [J]. arXiv preprint , 2018 , arXiv: 1802.05637 .

GAO X , ZHANG Z Y , DUAN L M . A quantum machine learning algorithm based on generative models [J]. Science Advances , 2018 , 4 ( 12 ): eaat9004 .

BENEDETTI M , GARCIA-PINTOS D , PERDOMO O , et al . A generative modeling approach for benchmarking and training shallow quantum circuits [J]. Npj Quantum Information , 2019 , 5 : 45 .

LLOYD S , WEEDBROOK C . Quantum generative adversarial learning [J]. Physical Review Letters , 2018 , 121 ( 4 ): 040502 .

SITU H Z , HE Z M , WANG Y Y , et al . Quantum generative adversarial network for generating discrete distribution [J]. Information Sciences , 2020 , 538 : 193 - 208 .

ZENG J F , WU Y F , LIU J G , et al . Learning and inference on generative adversarial quantum circuits [J]. Physical Review A , 2019 , 99 ( 5 ): 052306 .

BENEDETTI M , GRANT E , WOSSNIG L , et al . Adversarial quantum circuit learning for pure state approximation [J]. New Journal of Physics , 2019 , 21 ( 4 ): 043023 .

STAMATOPOULOS N , EGGER D J , SUN Y , et al . Option pricing using quantum computers [J]. Quantum , 2020 , 4 : 291 .

BARBEAU M , GARCIA-ALFARO J . Faking and discriminating the navigation data of a micro aerial vehicle using quantum generative adversarial networks [C]// IEEE Global Communications Conference . Waikoloa : IEEE , 2019 : 1 - 6 .

DALLAIRE-DEMERS P L , KILLORAN N . Quantum generative adversarial networks [J]. Physical Review A , 2018 , 98 ( 1 ): 012324 .

LIU W J , ZHANG Y , DENG Z L , et al . A hybrid quantum‑classical conditional generative adversarial network algorithm for human‑centered paradigm in cloud [J]. EURASIP Journal on Wireless Communications and Networking , 2021 , 2021 ( 1 ): 37 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

Wen-jie LIU

Jiao-jiao ZHAO

Ying ZHANG

Ye-bo GE

Related Institution

School of Computer and Software， Nanjing University of Information Science and Technology

School of Automation， Nanjing University of Information Science and Technology

⁰