中国物理B ›› 2025, Vol. 34 ›› Issue (7): 70302-070302.doi: 10.1088/1674-1056/adc7ed

• • 上一篇    下一篇

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. 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
  • 收稿日期:2024-11-17 修回日期:2025-02-15 接受日期:2025-04-02 出版日期:2025-06-18 发布日期:2025-07-07
  • 通讯作者: Chunhui Wu, Shengmei Zhao E-mail:wch13295016367@163.com;zhaosm@njupt.edu.cn
  • 基金资助:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 62375140 and 61871234).

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. 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
  • Received:2024-11-17 Revised:2025-02-15 Accepted:2025-04-02 Online:2025-06-18 Published:2025-07-07
  • Contact: Chunhui Wu, Shengmei Zhao E-mail:wch13295016367@163.com;zhaosm@njupt.edu.cn
  • Supported by:
    Project supported by the National Natural Science Foundation of China (Grant Nos. 62375140 and 61871234).

RichHTML

0

PDF (PC)

93

赞

摘要： 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.

关键词: quantum image processing, domain adaptation, quantum convolutional neural network, IBM quantum experience

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.

Key words: quantum image processing, domain adaptation, quantum convolutional neural network, IBM quantum experience

中图分类号:  (Quantum information)

  • 03.67.-a
03.67.Ac (Quantum algorithms, protocols, and simulations) 03.67.Bg (Entanglement production and manipulation) 03.67.Lx (Quantum computation architectures and implementations)