|
|
|
Domain adaptation method inspired by quantum convolutional neural network |
| Chunhui Wu(武春辉)1,†, Junhao Pei(裴骏豪)1, Yihua Wu(吴逸华)1, Anqi Zhang(张安琪)1, and Shengmei Zhao(赵生妹)1,2,3,‡ |
1 Institute of Signal Processing and Transmission, Nanjing University of Posts and Telecommunications (NUPT), Nanjing 210003, China;
2 Key Laboratory of Broadband Wireless Communication and Sensor Network Technology, Ministry of Education, Nanjing 210003, China;
3 National Laboratory of Solid State Microstructures, Nanjing University, Nanjing 210093, China |
|
|
|
|
Abstract Quantum machine learning is an important application of quantum computing in the era of noisy intermediate-scale quantum devices. Domain adaptation (DA) is an effective method for addressing the distribution discrepancy problem between the training data and the real data when the neural network model is deployed. In this paper, we propose a variational quantum domain adaptation method inspired by the quantum convolutional neural network, named variational quantum domain adaptation (VQDA). The data are first uploaded by a 'quantum coding module', then the feature information is extracted by several 'quantum convolution layers' and 'quantum pooling layers', which is named `Feature Extractor'. Subsequently, the labels and the domains of the samples are obtained by the 'quantum fully connected layer'. With a gradient reversal module, the trained 'Feature Extractor' can extract the features that cannot be distinguished from the source and target domains. The simulations on the local computer and IBM Quantum Experience (IBM Q) platform by Qiskit show the effectiveness of the proposed method. The results show that VQDA (with 8 quantum bits) has 91.46% average classification accuracy for DA task between MNIST$\rightarrow$USPS (USPS$\rightarrow$ MNIST), achieves 91.16% average classification accuracy for gray-scale and color images (with 10 quantum bits), and has 69.25% average classification accuracy on the DA task for color images (also with 10 quantum bits). VQDA achieves a 9.14% improvement in average classification accuracy compared to its corresponding classical domain adaptation method with the same parameter scale for different DA tasks. Simultaneously, the parameters scale is reduced to 43% by using VQDA when both quantum and classical DA methods have similar classification accuracies.
|
Received: 17 November 2024
Revised: 15 February 2025
Accepted manuscript online: 02 April 2025
|
|
PACS:
|
03.67.-a
|
(Quantum information)
|
| |
03.67.Ac
|
(Quantum algorithms, protocols, and simulations)
|
| |
03.67.Bg
|
(Entanglement production and manipulation)
|
| |
03.67.Lx
|
(Quantum computation architectures and implementations)
|
|
| Fund: Project supported by the National Natural Science Foundation of China (Grant Nos. 62375140 and 61871234). |
Corresponding Authors:
Chunhui Wu, Shengmei Zhao
E-mail: wch13295016367@163.com;zhaosm@njupt.edu.cn
|
Cite this article:
Chunhui Wu(武春辉), Junhao Pei(裴骏豪), Yihua Wu(吴逸华), Anqi Zhang(张安琪), and Shengmei Zhao(赵生妹) Domain adaptation method inspired by quantum convolutional neural network 2025 Chin. Phys. B 34 070302
|
[1] Fan C, Liu P, Xiao T, Zhao W and Tang X L 2020 Acta Autom. Sin. 46 515
[2] Wang M and Deng W 2018 Neurocomputing 312 135
[3] Tan C, Sun F, Kong T, ZhangW, Yang C and Liu C 2018 Artificial Neural Networks and Machine Learning-ICANN 2018: 27th International Conference on Artificial Neural Networks, October 4-7, 2018, Rhodes, Greece, p. 270
[4] Long M, Cao Y, Wang J and Jordan M 2015 Proceedings of the 32nd International Conference on Machine Learning, July 7-9, 2015, Lille, France, p. 97
[5] Rozantsev A, Salzmann M and Fua P 2018 IEEE Transactions on Pattern Analysis and Machine Intelligence 41 801
[6] Gong R, Li W, Chen Y and Gool L V 2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15- 20, 2019, Long Beach, USA, p. 2477
[7] Ma X, Zhang T and Xu C 2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 15-20, 2019, Long Beach, USA, p. 8258
[8] Zhuang F, Cheng X, Luo P, Pan S J and He Q 2015 Proceedings of the 24th International Conference on Artificial Intelligence, July 25, 2015, Buenos Aires, Argentina, p. 4119
[9] Kim T, Cha M, Kim H, Lee J K and Kim J 2017 Proceedings of the 34th International Conference on Machine Learning - Volume 70, August 6, 2017, Sydney, NSW, Australia, p. 1857
[10] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B,Warde-Farley D, Ozair S, Courville A and Bengio Y 2020 Commun. ACM 63 139
[11] Ganin Y, Ustinova E, Ajakan H, Germain P, Larochelle H, Laviolette F, March M and Lempitsky V 2016 The Journal of Machine Learning Research 17 2096
[12] Pan S J,Wan L C, Liu H L,Wu Y S, Qin S J,Wen Q Y and Gao F 2022 Chin. Phys. B 31 060304
[13] He X, Zhang A and Zhao S 2022 Quantum Inf. Process. 21 86
[14] Cerezo M, Verdon G, Huang H Y, Cincio L and Coles P J 2022 Nat. Comput. Sci. 2 567
[15] Hou Y Y, Li J, Chen X B and Tian Y 2022 Chin. Phys. B 31 030304
[16] Zhang A, He X and Zhao S 2022 Quantum Inf. Process. 21 358
[17] Schuld M and Killoran N 2019 Phys. Rev. Lett. 122 040504
[18] Wu Y, Wu C, Zhang A and Zhao S 2023 Quantum Inf. Process. 22 261
[19] Guo X Y, Li S S, Xiao X, Xiang Z C, Ge Z Y, Li H K, Song P T, Peng Y, Wang Z, Xu K and Zhang P 2023 Chin. Phys. B 32 010307
[20] Peruzzo A, McClean J, Shadbolt P, Yung M H, Zhou X Q, Love P J, Aspuru-Guzik A and O?brien J L 2014 Nat. Commun. 5 4213
[21] Chen R Y L, Zhao B C, Song Z X, Zhao X Q, Wang K and Wang X 2021 Acta Phys. Sin. 70 210302 (in Chinese)
[22] Zhang A,Wang K,Wu Y and Zhao S M 2023 Chin. Phys. B 32 100308
[23] Zhang A and Zhao S 2023 Quantum Inf. Process. 22 283
[24] Cong I, Choi S and Lukin M D 2019 Nat. Phys. 15 1273
[25] Hur T, Kim L and Park D K 2022 Quantum Machine Intelligence 4 3
[26] Lü Y, Gao Q, Lü J, Ogorzałek M and Zheng J 2021 2021 40th Chinese Control Conference (CCC), July 26-28, 2021, Shanghai, China, p. 6329
[27] Yang C H H, Qi J, Chen S Y C, Chen P Y, Siniscalchi S M, Ma X and Lee C H 2021 ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), June 6-11, 2021, Toronto, ON, Canada, p. 6523
[28] Wei S, Chen Y, Zhou Z and Long G 2022 AAPPS Bull. 32 1
[29] Yao X W, Wang H, Liao Z, Chen M C, Pan J, Li J, Zhang K, Lin X, Wang Z, Luo Z and Zheng W 2017 Phys. Rev. X 7 031041
[30] Zhang K, Hsieh M H, Liu L and Tao D 2020 arXiv:2011.06258 [quantph]
[31] Shende V V, Markov I L and Bullock S S 2004 Phys. Rev. A 69 062321
[32] Nielsen M A and Chuang I L 2010 Quantum Computation and Quantum Information, 10th Anniversary Edition. (Cambridge: Cambridge University Press) pp. 186-187
[33] Schuld M, Bocharov A, Svore K M and Wiebe N 2020 Phys. Rev. A 101 032308
[34] Amari S 2016 Information Geometry and Its Applications (Springer Tokyo) Vol. 194 |
| No Suggested Reading articles found! |
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
Altmetric
|
|
blogs
Facebook pages
Wikipedia page
Google+ users
|
Online attention
Altmetric calculates a score based on the online attention an article receives. Each coloured thread in the circle represents a different type of online attention. The number in the centre is the Altmetric score. Social media and mainstream news media are the main sources that calculate the score. Reference managers such as Mendeley are also tracked but do not contribute to the score. Older articles often score higher because they have had more time to get noticed. To account for this, Altmetric has included the context data for other articles of a similar age.
View more on Altmetrics
|
|
|
