Skip to main content
SpringerLink
Log in

Quantum classification algorithm with multi-class parallel training

  • Published:
Quantum Information Processing Aims and scope Submit manuscript

Abstract

Using the properties of quantum superposition, we propose a quantum classification algorithm to efficiently perform multi-class classification tasks, where the training data are loaded into parameterized operators which are applied to the basis of the quantum state in quantum circuit composed by sample register and label register, and the parameters of quantum gates are optimized by a hybrid quantum-classical method, which is composed of a trainable quantum circuit and a gradient-based classical optimizer. After several quantum-to-class repetitions, the quantum state is optimal that the state in sample register is the same as that in label register. For a classification task of L-class, the analysis shows that the space and time complexity of the quantum circuit are \(O(L*logL)\) and O(logL), respectively. The numerical simulation results of 2-class task and 5-class task show that the proposed algorithm has a higher classification accuracy, faster convergence and higher expression ability. The classification accuracy and the speed of converging can also be improved by increasing the number times of applying multi-qubit-controlled operators on the quantum circuit, especially for multiple classes classification.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data availability

All data and models generated or used during the study appear in the submitted article.

References

  1. Logesh, K., Madane, S.S.R.: Improved CLC routing protocol with node classification algorithm for manet. Appl. Math. 12(5), 1013–1019 (2018)

    Google Scholar 

  2. Mandal, J.K., Bhattacharya, D.: Emerging Technology in Modelling and Graphics. Springer, Berlin (2020)

    Book  Google Scholar 

  3. Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., Gao, J.: Deep learning-based text classification: a comprehensive review. ACM Comput. Surv. (CSUR) 54(3), 1–40 (2021)

    Article  Google Scholar 

  4. Abdel-Aty, A.H., Kadry, H., Zidan, M., Al-Sbou, Y., Zanaty, E., Abdel-Aty, M.: A quantum classification algorithm for classification incomplete patterns based on entanglement measure. J. Intell. Fuzzy Syst. 38(3), 2809–2816 (2020)

    Article  Google Scholar 

  5. Zidan, M., Abdel-Aty, A.H., Nguyen, D.M., Mohamed, A.S., Al-Sbou, Y., Eleuch, H., Abdel-Aty, M.: A quantum algorithm based on entanglement measure for classifying boolean multivariate function into novel hidden classes. Results Phys. 15, 102549 (2019)

    Article  Google Scholar 

  6. Lakshmi, S.A., Mary, S.: Group mosquito host seeking algorithm based self organizing technique for genetic algorithm. Appl. Math. Inform. Sci 13, 231–238 (2019)

    Article  Google Scholar 

  7. Emam, O., Abdel-Fattah, M.A., Azzam, S.M.: A decomposition algorithm for solving multi-level large-scale linear programming problems with neutrosophic parameters in the constrains. Appl. Math. 14(5), 913–919 (2020)

    MathSciNet  Google Scholar 

  8. Harrow, A.W., Hassidim, A., Lloyd, S.: Quantum algorithm for linear systems of equations. Phys. Rev. L. 103(15), 150502 (2009)

    Article  MathSciNet  ADS  Google Scholar 

  9. Macaluso, A., Clissa, L., Lodi, S., Sartori, C.: Quantum ensemble for classification. arXiv:2007.01028 (2020)

  10. Aaronson, S.: Read the fine print. Nat. Phys. 11(4), 291–293 (2015)

    Article  Google Scholar 

  11. Tawhid, M.A., Paluck, G.: Solving linear bilevel programming via particle swarm algorithm with heuristic pattern searc. Inf. Sci. Lett. 6(1), 1 (2021)

    Google Scholar 

  12. Zidan, M., Aldulaimi, S., Eleuch, H.: Analysis of the quantum algorithm based on entanglement measure for classifying boolean multivariate function into novel hidden classes: revisited. Appl. Math. Inform. Sci. 15(5), 643–647 (2021)

    Article  MathSciNet  Google Scholar 

  13. Biamonte, J., Wittek, P., Pancotti, N., Rebentrost, P., Wiebe, N., Lloyd, S.: Quantum machine learning. Nature 549(7671), 195–202 (2017)

    Article  ADS  Google Scholar 

  14. Wan, K.H., Dahlsten, O., Kristjánsson, H., Gardner, R., Kim, M.: Quantum generalisation of feedforward neural networks. NPJ Quantum Inform. 3(1), 1–8 (2017)

    Article  Google Scholar 

  15. Torrontegui, E., García-Ripoll, J.J.: Unitary quantum perceptron as efficient universal approximator (a). EPL (Eur. Lett.) 125(3), 30004 (2019)

    Article  ADS  Google Scholar 

  16. Lloyd, S., Mohseni, M., Rebentrost, P.: Quantum algorithms for supervised and unsupervised machine learning. arXiv:1307.0411 (2013)

  17. Rebentrost, P., Mohseni, M., Lloyd, S.: Quantum support vector machine for big data classification. Phys. Rev. L. 113(13), 130503 (2014)

    Article  ADS  Google Scholar 

  18. Farhi, E., Neven, H.: Classification with quantum neural networks on near term processors. arXiv:1802.06002 (2018)

  19. Mari, A., Bromley, T.R., Izaac, J., Schuld, M., Killoran, N.: Transfer learning in hybrid classical-quantum neural networks. Quantum 4, 340 (2020)

    Article  Google Scholar 

  20. Wang, S.: A shifted power method for homogenous polynomial optimization over unit spheres. J. Math. Res. 7(2), 175 (2015)

    Article  Google Scholar 

  21. Schuld, M., Killoran, N.: Quantum machine learning in feature Hilbert spaces. Phys. Rev. L. 122(4), 040504 (2019)

    Article  ADS  Google Scholar 

  22. Gilyén, A., Arunachalam, S., Wiebe, N.: Optimizing quantum optimization algorithms via faster quantum gradient computation. In: Proceedings of the Thirtieth annual ACM-SIAM symposium on discrete algorithms, pp. 1425–1444. SIAM (2019)

  23. Zidan, M., Abdel-Aty, A.H., El-shafei, M., Feraig, M., Al-Sbou, Y., Eleuch, H., Abdel-Aty, M.: Quantum classification algorithm based on competitive learning neural network and entanglement measure. Appl. Sci. 9(7), 1277 (2019)

    Article  Google Scholar 

  24. Chalumuri, A., Kune, R., Manoj, B.: A hybrid classical-quantum approach for multi-class classification. Quantum Inf. Process. 20(3), 1–19 (2021)

    Article  MathSciNet  Google Scholar 

  25. Wiebe, N., Braun, D., Lloyd, S.: Quantum algorithm for data fitting. Phys. Rev. L. 109(5), 050505 (2012)

    Article  ADS  Google Scholar 

  26. Schuld, M., Fingerhuth, M., Petruccione, F.: Implementing a distance-based classifier with a quantum interference circuit. EPL (Eur. Lett.) 119(6), 60002 (2017)

    Article  ADS  Google Scholar 

  27. Otterbach, J.S., Manenti, R., Alidoust, N., Bestwick, A., Block, M., Bloom, B., Caldwell, S., Didier, N., Fried, E.S., Hong, S., et al.: Unsupervised machine learning on a hybrid quantum computer. arXiv:1712.05771 (2017)

  28. Grant, E., Benedetti, M., Cao, S., Hallam, A., Lockhart, J., Stojevic, V., Green, A.G., Severini, S.: Hierarchical quantum classifiers. NPJ quantum. Inform 4(1), 1–8 (2018)

    Google Scholar 

  29. Havlíček, V., Córcoles, A.D., Temme, K., Harrow, A.W., Kandala, A., Chow, J.M., Gambetta, J.M.: Supervised learning with quantum-enhanced feature spaces. Nature 567(7747), 209–212 (2019)

    Article  ADS  Google Scholar 

  30. Adhikary, S., Dangwal, S., Bhowmik, D.: Supervised learning with a quantum classifier using multi-level systems. Quantum Inf. Process. 19(3), 1–12 (2020)

    Article  MathSciNet  Google Scholar 

  31. Chen, S.Y.C., Huang, C.M., Hsing, C.W., Kao, Y.J.: An end-to-end trainable hybrid classical-quantum classifier. Mach. Learn.: Sci. Technol. 2(4), 045021 (2021)

    Google Scholar 

  32. Bhatia, A.S., Saggi, M.K., Kumar, A., Jain, S.: Matrix product state-based quantum classifier. Neural Comput. 31(7), 1499–1517 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  33. Pérez-Salinas, A., Cervera-Lierta, A., Gil-Fuster, E., Latorre, J.I.: Data re-uploading for a universal quantum classifier. Quantum 4, 226 (2020)

    Article  Google Scholar 

  34. Adhikary, S.: An entanglement enhanced training algorithm for supervised quantum classifiers. arXiv:2006.13302 (2020)

  35. Beer, K., Bondarenko, D., Farrelly, T., Osborne, T.J., Salzmann, R., Scheiermann, D., Wolf, R.: Training deep quantum neural networks. Nat. Commun. 11(1), 1–6 (2020)

    Article  Google Scholar 

  36. Nielsen, M.A., Chuang, I.: Quantum computation and quantum information (2002)

  37. Comelli, P., Ferragina, P., Granieri, M.N., Stabile, F.: Optical recognition of motor vehicle license plates. IEEE Trans. Veh. Technol. 44(4), 790–799 (1995)

    Article  Google Scholar 

  38. Bergholm, V., Izaac, J., Schuld, M., Gogolin, C., Alam, M.S., Ahmed, S., Arrazola, J.M., Blank, C., Delgado, A., Jahangiri, S., et al.: Pennylane: automatic differentiation of hybrid quantum-classical computations. arXiv:1811.04968 (2018)

Download references

Acknowledgements

This work is supported by the National Natural Science Foundation of China (61871234), and Postgraduate Research and Practice Innovation Program of Jiangsu Province (Grant KYCX19_0900).

Author information

Authors and Affiliations

  1. Institute of Signal Processing Transmission, Nanjing University of Posts and Telecommunications (NUPT), Nanjing, 210003, China

    Anqi Zhang, Xiaoyun He & Shengmei Zhao

  2. Key Lab of Broadband Wireless Communication and Sensor Network Technology, Ministry of Education, Nanjing, 210003, China

    Shengmei Zhao

Authors
  1. Anqi Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoyun He
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shengmei Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shengmei Zhao.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, A., He, X. & Zhao, S. Quantum classification algorithm with multi-class parallel training. Quantum Inf Process 21, 358 (2022). https://doi.org/10.1007/s11128-022-03700-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11128-022-03700-9

Keywords

Search

Navigation