Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2005.03355 · Physical Review A

Quantum correlation alignment for unsupervised domain adaptation

Xi He

Published Sep 16, 2020• 14 citations
arXivHTMLPDF

Abstract

The correlation alignment algorithm (CORAL), a representative domain adaptation algorithm, decorrelates and aligns a labeled source domain dataset to an unlabeled target domain dataset to minimize the domain shift such that a classifier can be applied to predict the target domain labels. In this paper, we implement the CORAL on quantum devices by two different methods. One method utilizes quantum basic linear algebra subroutines to implement the CORAL with exponential speedup in the number and dimension of the given data samples. The other method is achieved through a variational hybrid quantum-classical procedure. In addition, the numerical experiments of the CORAL with three different types of data sets, namely, the synthetic data, the synthetic-Iris data, and the handwritten digit data, are presented to evaluate the performance of our paper. The simulation results prove that the variational quantum correlation alignment algorithm can achieve competitive performance compared with the classical CORAL.

DOI
10.1103/physreva.102.032410

Related papers

Quantum subspace alignment for domain adaptation

Xi He

Domain adaptation (DA) is used for adaptively obtaining labels of an unprocessed data set with a given related, but different labeled data set. Subspace alignment (SA), a representative DA algorithm, attempts to find a linear transformation to align the subspaces of the two different data sets. The classifier trained on the aligned labeled data set can be transferred to the unlabeled data set to predict the target labels. In this paper, two quantum versions of the SA are proposed to implement the DA procedure on quantum devices. One method, the quantum subspace alignment algorithm (QSA), can achieve quadratic speedup in the number and dimension of given samples. The other method, the variational quantum subspace alignment algorithm (VQSA), can be implemented on near-term quantum devices through a variational hybrid quantum-classical procedure. The results of the numerical experiments on different types of data sets demonstrate that the VQSA can achieve high accuracy in dealing with DA tasks.

arXiv:2001.02472•Physical Review A•Dec 2, 2020•9 citations

Quantum kernel subspace alignment for unsupervised domain adaptation

Xi He, Feiyu Du

Domain adaptation (DA), the sub-realm of the transfer learning, attempts to deal with machine learning tasks on an unprocessed data domain with the different, but related labeled source domain. However, the classical DA can not efficiently deal with the cross-domain tasks in quantum mechanical scenarios. In this paper, the quantum kernel subspace alignment algorithm is proposed to achieve the procedure of DA by extracting the non-linear features with the quantum kernel method and aligning the two domains with the unitary evolution. The method presented in our work can be implemented on the universal quantum computer with the quantum basic linear algebra subroutines. Based on the algorithmic complexity analysis, the procedure of the QKSA can be implemented with at least quadratic quantum speedup compared with the classical DA algorithms.

Asia Conference on Algorithms, Computing and Machine Learning (CACML)•Mar 17, 2023•0 citations

Learning from imperfect quantum data via unsupervised domain adaptation with classical shadows

Kosuke Ito, Akira Tanji, Hiroshi Yano +2 more

Learning from quantum data using classical machine learning models has emerged as a promising paradigm toward realizing quantum advantages. Despite extensive analyses on their performance, clean and fully labeled quantum data from the target domain are often unavailable in practical scenarios, forcing models to be trained on data collected under conditions that differ from those encountered at deployment. This mismatch highlights the need for new approaches beyond the common assumptions of prior work. In this work, we address this issue by employing an unsupervised domain adaptation framework for learning from imperfect quantum data. Specifically, by leveraging classical representations of quantum states obtained via classical shadows, we perform unsupervised domain adaptation entirely within a classical computational pipeline once measurements on the quantum states are executed. We numerically evaluate the framework on quantum phases of matter and entanglement classification tasks under realistic domain shifts. Across both tasks, our method outperforms source-only non-adaptive baselines and target-only unsupervised learning approaches, demonstrating the practical applicability of domain adaptation to realistic quantum data learning.

quant-pharXiv:2603.28294•Mar 31, 2026•0 citations

Quantum transfer component analysis for domain adaptation

Xi He, Chufan Lyu, Min-Hsiu Hsieh +1 more

Domain adaptation, a crucial sub-field of transfer learning, aims to utilize known knowledge of one data set to accomplish tasks on another data set. In this paper, we perform one of the most representative domain adaptation algorithms, transfer component analysis (TCA), on quantum devices. Two different quantum implementations of this transfer learning algorithm; namely, the linear-algebra-based quantum TCA algorithm and the variational quantum TCA algorithm, are presented. The algorithmic complexity of the linear-algebra-based quantum TCA algorithm is $O(\mathrm{poly}(\log (n_{s} + n_{t})))$, where $n_{s}$ and $n_{t}$ are input sample size. Compared with the corresponding classical algorithm, the linear-algebra-based quantum TCA can be performed on a universal quantum computer with exponential speedup in the number of given samples. Finally, the variational quantum TCA algorithm based on a quantum-classical hybrid procedure, that can be implemented on the near term quantum devices, is proposed.

arXiv:1912.09113•Dec 19, 2019•1 citation

Distribution alignment based transfer fusion frameworks on quantum devices for seeking quantum advantages

He, Xi, Feiyu Du, Xiaohan Yu +2 more

The scarcity of labelled data is specifically an urgent challenge in the field of quantum machine learning (QML). Two transfer fusion frameworks are proposed in this paper to predict the labels of a target domain data by aligning its distribution to a different but related labelled source domain on quantum devices. The frameworks fuses the quantum data from two different, but related domains through a quantum information infusion channel. The predicting tasks in the target domain can be achieved with quantum advantages by post-processing quantum measurement results. One framework, the quantum basic linear algebra subroutines (QBLAS) based implementation, can theoretically achieve the procedure of transfer fusion with quadratic speedup on a universal quantum computer. In addition, the other framework, a hardware-scalable architecture, is implemented on the noisy intermediate-scale quantum (NISQ) devices through a variational hybrid quantum-classical procedure. Numerical experiments on the synthetic and handwritten digits datasets demonstrate that the variatioinal transfer fusion (TF) framework can reach state-of-the-art (SOTA) quantum DA method performance.

arXiv:2411.01822•Nov 4, 2024•0 citations

Quantum Joint Distribution Adaptation on the Universal Quantum Computer

Feiyu Du, Xi He

Transfer learning (TL) is one of the most important sub-realms in the field of machine learning. The goal is to achieve knowledge transfer from source domain to target domain by utilizing the similarities among data, tasks, or models. Domain adaptation (DA) is actually a type of transductive TL with assumption that both the marginal and the conditional distribution adaptation are different. In this paper, the process of joint distribution adaptation implemented on the universal quantum computer is presented. Compared to the classical joint distribution adaptation, the performance and application scope of the algorithm are promoted by the advantages of the quantum operations. Specifically, the quantum joint distribution adaptation algorithm proposed in our work can be performed exponentially efficient with quantum computing techniques in contrast to the corresponding classical procedure.

International Conference on Pattern Recognition and Artificial Intelligence (PRAI)•Aug 18, 2023•0 citations
The correlation alignment algorithm (CORAL), a representative domain adaptation algorithm, decorrelates and aligns a labeled source domain dataset to an unlabeled target domain dataset to minimize the domain shift such that a classifier can be applied to predict the target domain labels. In this paper, we implement the CORAL on quantum devices by two different methods. One method utilizes quantum basic linear algebra subroutines to implement the CORAL with exponential speedup in the number and dimension of the given data samples. The other method is achieved through a variational hybrid quantum-classical procedure. In addition, the numerical experiments of the CORAL with three different types of data sets, namely, the synthetic data, the synthetic-Iris data, and the handwritten digit data, are presented to evaluate the performance of our paper. The simulation results prove that the variational quantum correlation alignment algorithm can achieve competitive performance compared with the classical CORAL.
Domain adaptation (DA) is used for adaptively obtaining labels of an unprocessed data set with a given related, but different labeled data set. Subspace alignment (SA), a representative DA algorithm, attempts to find a linear transformation to align the subspaces of the two different data sets. The classifier trained on the aligned labeled data set can be transferred to the unlabeled data set to predict the target labels. In this paper, two quantum versions of the SA are proposed to implement the DA procedure on quantum devices. One method, the quantum subspace alignment algorithm (QSA), can achieve quadratic speedup in the number and dimension of given samples. The other method, the variational quantum subspace alignment algorithm (VQSA), can be implemented on near-term quantum devices through a variational hybrid quantum-classical procedure. The results of the numerical experiments on different types of data sets demonstrate that the VQSA can achieve high accuracy in dealing with DA tasks.
Domain adaptation (DA), the sub-realm of the transfer learning, attempts to deal with machine learning tasks on an unprocessed data domain with the different, but related labeled source domain. However, the classical DA can not efficiently deal with the cross-domain tasks in quantum mechanical scenarios. In this paper, the quantum kernel subspace alignment algorithm is proposed to achieve the procedure of DA by extracting the non-linear features with the quantum kernel method and aligning the two domains with the unitary evolution. The method presented in our work can be implemented on the universal quantum computer with the quantum basic linear algebra subroutines. Based on the algorithmic complexity analysis, the procedure of the QKSA can be implemented with at least quadratic quantum speedup compared with the classical DA algorithms.
Learning from quantum data using classical machine learning models has emerged as a promising paradigm toward realizing quantum advantages. Despite extensive analyses on their performance, clean and fully labeled quantum data from the target domain are often unavailable in practical scenarios, forcing models to be trained on data collected under conditions that differ from those encountered at deployment. This mismatch highlights the need for new approaches beyond the common assumptions of prior work. In this work, we address this issue by employing an unsupervised domain adaptation framework for learning from imperfect quantum data. Specifically, by leveraging classical representations of quantum states obtained via classical shadows, we perform unsupervised domain adaptation entirely within a classical computational pipeline once measurements on the quantum states are executed. We numerically evaluate the framework on quantum phases of matter and entanglement classification tasks under realistic domain shifts. Across both tasks, our method outperforms source-only non-adaptive baselines and target-only unsupervised learning approaches, demonstrating the practical applicability of domain adaptation to realistic quantum data learning.
Domain adaptation, a crucial sub-field of transfer learning, aims to utilize known knowledge of one data set to accomplish tasks on another data set. In this paper, we perform one of the most representative domain adaptation algorithms, transfer component analysis (TCA), on quantum devices. Two different quantum implementations of this transfer learning algorithm; namely, the linear-algebra-based quantum TCA algorithm and the variational quantum TCA algorithm, are presented. The algorithmic complexity of the linear-algebra-based quantum TCA algorithm is O(poly(log⁡(ns+nt)))O(\mathrm{poly}(\log (n_{s} + n_{t})))O(poly(log(ns​+nt​))), where nsn_{s}ns​ and ntn_{t}nt​ are input sample size. Compared with the corresponding classical algorithm, the linear-algebra-based quantum TCA can be performed on a universal quantum computer with exponential speedup in the number of given samples. Finally, the variational quantum TCA algorithm based on a quantum-classical hybrid procedure, that can be implemented on the near term quantum devices, is proposed.
The scarcity of labelled data is specifically an urgent challenge in the field of quantum machine learning (QML). Two transfer fusion frameworks are proposed in this paper to predict the labels of a target domain data by aligning its distribution to a different but related labelled source domain on quantum devices. The frameworks fuses the quantum data from two different, but related domains through a quantum information infusion channel. The predicting tasks in the target domain can be achieved with quantum advantages by post-processing quantum measurement results. One framework, the quantum basic linear algebra subroutines (QBLAS) based implementation, can theoretically achieve the procedure of transfer fusion with quadratic speedup on a universal quantum computer. In addition, the other framework, a hardware-scalable architecture, is implemented on the noisy intermediate-scale quantum (NISQ) devices through a variational hybrid quantum-classical procedure. Numerical experiments on the synthetic and handwritten digits datasets demonstrate that the variatioinal transfer fusion (TF) framework can reach state-of-the-art (SOTA) quantum DA method performance.
Transfer learning (TL) is one of the most important sub-realms in the field of machine learning. The goal is to achieve knowledge transfer from source domain to target domain by utilizing the similarities among data, tasks, or models. Domain adaptation (DA) is actually a type of transductive TL with assumption that both the marginal and the conditional distribution adaptation are different. In this paper, the process of joint distribution adaptation implemented on the universal quantum computer is presented. Compared to the classical joint distribution adaptation, the performance and application scope of the algorithm are promoted by the advantages of the quantum operations. Specifically, the quantum joint distribution adaptation algorithm proposed in our work can be performed exponentially efficient with quantum computing techniques in contrast to the corresponding classical procedure.