Quantum classifiers for domain adaptation

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.

Automated summary

Transfer learning is a crucial subfield of machine learning that aims to accomplish a task in the target domain with the knowledge acquired from the source domain. This paper presents two quantum implementations of domain adaptation classifiers that achieve quantum speedup compared to classical classifiers. One implementation uses quantum basic linear algebra subroutines to predict labels with logarithmic resources. The other implementation efficiently accomplishes the domain adaptation task through a variational hybrid quantum-classical procedure.