Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/27116
Title: Quantum classifiers for domain adaptation
Authors: He, X
Du, F
Xue, M
Du, X
Lei, T
Nandi, AK
Keywords: domain adaptation;quantum machine learning;transfer learning;quantum algorithm;machine learning
Issue Date: 6-Feb-2023
Publisher: Springer Nsture
Citation: He, X. et al. (2023) 'Quantum classifiers for domain adaptation', Quantum Information Processing, 22 (2), 105, pp. 1 - 13. doi: 10.1007/s11128-023-03846-0.
Abstract: Transfer learning (TL), a crucial subfield of machine learning, aims to accomplish a task in the target domain with the acquired knowledge of the source domain. Specifically, effective domain adaptation (DA) facilitates the delivery of the TL task where all the data samples of the two domains are distributed in the same feature space. In this paper, two quantum implementations of the DA classifier are presented with quantum speedup compared with the classical DA classifier. One implementation, the quantum basic linear algebra subroutines-based classifier, can predict the labels of the target domain data with logarithmic resources in the number and dimension of the given data. The other implementation efficiently accomplishes the DA task through a variational hybrid quantum-classical procedure.
Description: The file archived on this institutional repository is a preprint - arXiv:2110.02808v1 [quant-ph] for this version) https://doi.org/10.48550/arXiv.2110.02808. It has not been cerified by peer review. Please consult the final, corrected version published by Springer Nature at https://doi.org/10.1007/s11128-023-03846-0.
URI: https://bura.brunel.ac.uk/handle/2438/27116
DOI: https://doi.org/10.1007/s11128-023-03846-0
ISSN: 1570-0755
Other Identifiers: ORCID iD: Asoke K. Nandi https://orcid.org/0000-0001-6248-2875
Article number: 105
Appears in Collections:Dept of Electronic and Electrical Engineering Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2021 The authors. This version of the article is a preprint available at: https://arxiv.org/abs/2110.02808, it is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s11128-023-03846-0 (see: https://arxiv.org/licenses/nonexclusive-distrib/1.0/license.html)8.28 MBAdobe PDFView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.