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

Scientific Reports

Scalable parameterized quantum circuits classifier

Xiaodong Ding, Zhihui Song, Jinchen Xu, Yifan Hou, Tian Yang, Zheng Shan

Published Jul 10, 2024• 26 citations
Publisher

Abstract

As a generalized quantum machine learning model, parameterized quantum circuits (PQC) have been found to perform poorly in terms of classification accuracy and model scalability for multi-category classification tasks. To address this issue, we propose a scalable parameterized quantum circuits classifier (SPQCC), which performs per-channel PQC and combines the measurements as the output of the trainable parameters of the classifier. By minimizing the cross-entropy loss through optimizing the trainable parameters of PQC, SPQCC leads to a fast convergence of the classifier. The parallel execution of identical PQCs on different quantum machines with the same structure and scale reduces the complexity of classifier design. Classification simulations performed on the MNIST Dataset show that the accuracy of our proposed classifier far exceeds that of other quantum classification algorithms, achieving the state-of-the-art simulation result and surpassing/reaching classical classifiers with a considerable number of trainable parameters. Our classifier demonstrates excellent scalability and classification performance.

DOI
10.1038/s41598-024-66394-2

Related papers

Parameterized quantum circuit for binary and multi classification

S. Megala, P. Ragukumar, Neelu Khare

Machine learning models achieve strong predictive performance by uncovering hidden patterns and structures within data. Quantum Machine Learning (QML) extends this capability by leveraging principles of quantum mechanics to address complex classification tasks. However, designing effective feature extraction strategies remains challenging. The choice of ansatz plays a central role in determining the expressive power and learning capability of quantum models. In this work, we propose a parameterized quantum circuit model incorporating adaptive transformations between neighboring qubits to enhance feature extraction and classification performance. The proposed approach is evaluated on seven benchmark datasets from the UCI repository: Iris, Banknote Authentication (BNA), Raisin, Wireless Indoor Localization (WIL), Wine, Penguin, and HTRU2. Its performance is compared against existing quantum classification models, including the Amplitude Embedding Model (AEM), Variational Quantum Circuit (VQC), and Quantum Multi-Class Classifier (QMCC), using identical numbers of layers and training epochs. Additionally, comparisons are made with well-established standard classical classifiers. Experimental results implemented on the PennyLane platform demonstrate that the proposed model achieves high test accuracies within only 10–15 training epochs, reaching 100% (Iris), 98.3% (BNA), 91.1% (Raisin), 97.0% (WIL), 99.2% (Penguin), 94.0% (Wine), and 95.4% (HTRU2). These findings indicate that the proposed ansatz effectively extracts meaningful features and performs competitively in both binary and multi-class classification tasks, highlighting its potential for practical quantum machine learning applications.

Array•Jun 10, 2026•1 citation

HQCC: A Hybrid Quantum-Classical Classifier With Adaptive Structure

Ren-Xin Zhao, Harun Šiljak, Shi Wang +2 more

Parameterized Quantum Circuits (PQCs) with fixed structures severely degrade the performance of Quantum Machine Learning (QML). To address this, a Hybrid Quantum-Classical Classifier (HQCC) is proposed. It adaptively optimizes the PQC through a dynamic circuit generator driven by Long Short Term Memory (LSTM) and exploits architectural plasticity to balance the entanglement performance and expressiveness, opening up a practical pathway for efficiently deploying QML in the Noisy Intermediate-Scale Quantum (NISQ) era. Extensive experiments on MNIST and Fashion-MNIST demonstrate that HQCC achieves up to 99.86% accuracy in binary classification and 97.12% in multi-class tasks, surpassing state-of-the-art quantum and classical baselines.

arXiv:2504.02167•IEEE Signal Processing Letters•Jan 1, 2025•4 citations

Quantum Kernel-Based Classification: An Optimized Quantum Support Vector Classifier Approach

Xiaoman Liu

Quantum machine learning has emerged as a promising frontier, leveraging the principles of quantum computing to enhance classical algorithms. This paper proposes an optimized Quantum Support Vector Classifier (QSVC) for the classification of the MNIST dataset (a benchmark in handwritten digit recognition). We employ a Chebyshev Parameterized Quantum Circuit (PQC) with an increased number of qubits and layers, and utilize an existing projected quantum kernel method to effectively capture the complex patterns in the data. To enhance model robustness, data augmentation techniques are applied, and dimensionality reduction is performed using Principal Component Analysis (PCA). The proposed QSVC demonstrates competitive accuracy on both the training and testing datasets, highlighting the potential of quantum kernel methods in practical machine learning applications. A comparative analysis with classical Support Vector Machines (SVM) demonstrates the feasibility of quantum methods for high-dimensional classification tasks. Additionally, we investigate the impact of varying the number of qubits in the quantum circuit, providing in-depth insights into the scalability and performance trade-offs of quantum kernel methods.

IEEE International Conference on Frontiers Technology of Information and Computer (ICFTIC)•Dec 13, 2024•0 citations

Enhanced natural parameterized quantum circuit

Yuquan Chen, Yanjun Hou, Zeyuan Wang +4 more

The classical-quantum interface for loading classical data into quantum systems is an indispensable component of quantum information processing, and the parameterized quantum circuit (PQC) represents significant methodology in this area. However, a challenge in designing parameterized quantum circuits that can fully utilize limited qubit resources while accurately representing classical data remains. To address this issue, we propose the enhanced natural parameterized quantum circuit (ENPQC), which achieves the maximum parameter capacity of quantum systems and preserves the local structure of the original dataset. To make the encoding circuits more experiment friendly, we further provide two near-optimal circuits that achieve near-maximum capacity and are comparable in complexity to the existing PQCs. We numerically show that the ENPQC overwhelms other encoding methods for multiple datasets, demonstrating its potential for machine learning tasks. Furthermore, we experimentally validate our scheme by demonstrating a three-class classification task on an NMR platform, which achieves over 97 % accuracy. This work provides a powerful tool for the classical-quantum interface, paving the way for quantum big data processing during the noisy intermediate-scale quantum era.

Physical Review Research•Feb 27, 2025•5 citations

Improved Quantum Two-Classification Network *

Shuang Cong, Jingru Qiu

An improved quantum neural network based on a parameterized quantum circuit for 0 or 1 classification of images is designed in this paper. A classical handwritten digital image of size$28 \times 28$pixels is compressed into a$4 \times 4$pixel image, whose 16 classical images represent the probability amplitudes of a 4-qubit state input in the quantum state preparation circuit. The output and corresponding 0 or 1 labels are used as training data for supervised learning of a parameterized quantum recognition circuit composed of 4 qubits. The complete design process is studied in detail, including the input of classical data, quantum state preparation, the output recognition of images by the parameterized quantum circuit, and the projection measurement of the designated readout qubit. In the training of the network parameters, the goal of minimizing the loss function is to achieve optimal quantum circuit parameters. In the performance comparison experiments, handwritten digital images from the MNIST dataset are used to conduct recognition tests on two specific digits, and the test accuracy is 98.88%. The recognition accuracy rate increases by 8.13% compared with the recognition performance before the improvement. The quantum image recognition network designed in this paper can be extended to multiclass classification applications.

International Conference on Control and Automation•Jun 1, 2026•0 citations

HN-PQE: Hardware-Native Parameterized Quantum Embedding for Noise-Resilient Classifications of Medical Signals and Images

Philipp Moser, Alexander Maletzky, Michael Giretzlehner

Quantum neural networks are a popular realization of quantum machine learning. Typically, classical data is first embedded into the state vector of a quantum system. A parameterized quantum circuit (PQC) then acts on the quantum state, with its trainable parameters continuously adjusted during the optimization process. However, current quantum hardware faces challenges, such as accumulating noise with increasing circuit complexity and a limited set of native gate operations. As a result, transpiling quantum circuits to real hardware often increases the number of the required gate instructions. These factors set considerable constraints on the accuracy of quantum machine learning models. To address these limitations, we propose a novel quantum neural network architecture, termed hardware-native parameterized quantum embedding (HN-PQE). Our approach offers two key advantages: First, HN-PQE exclusively employs the native gates of IBM's current Eagle quantum processor family, ensuring that the gate count remains stable during transpilation. Second, by combining data embedding with the PQC, HN-PQE achieves a highly compact circuit design. We empirically validate our approach on two classification tasks, simulating both idealized (no hardware noise) and noisy conditions (mimicking IBM's Brisbane device). When compared to two popular quantum neural networks, HN-PQE showed similar performance in idealized scenarios but demonstrated significant noise resilience under hardware-noise conditions. This resilience makes HN-PQE a promising candidate for future quantum machine learning experiments on real hardware.

IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•1 citation
As a generalized quantum machine learning model, parameterized quantum circuits (PQC) have been found to perform poorly in terms of classification accuracy and model scalability for multi-category classification tasks. To address this issue, we propose a scalable parameterized quantum circuits classifier (SPQCC), which performs per-channel PQC and combines the measurements as the output of the trainable parameters of the classifier. By minimizing the cross-entropy loss through optimizing the trainable parameters of PQC, SPQCC leads to a fast convergence of the classifier. The parallel execution of identical PQCs on different quantum machines with the same structure and scale reduces the complexity of classifier design. Classification simulations performed on the MNIST Dataset show that the accuracy of our proposed classifier far exceeds that of other quantum classification algorithms, achieving the state-of-the-art simulation result and surpassing/reaching classical classifiers with a considerable number of trainable parameters. Our classifier demonstrates excellent scalability and classification performance.
Machine learning models achieve strong predictive performance by uncovering hidden patterns and structures within data. Quantum Machine Learning (QML) extends this capability by leveraging principles of quantum mechanics to address complex classification tasks. However, designing effective feature extraction strategies remains challenging. The choice of ansatz plays a central role in determining the expressive power and learning capability of quantum models. In this work, we propose a parameterized quantum circuit model incorporating adaptive transformations between neighboring qubits to enhance feature extraction and classification performance. The proposed approach is evaluated on seven benchmark datasets from the UCI repository: Iris, Banknote Authentication (BNA), Raisin, Wireless Indoor Localization (WIL), Wine, Penguin, and HTRU2. Its performance is compared against existing quantum classification models, including the Amplitude Embedding Model (AEM), Variational Quantum Circuit (VQC), and Quantum Multi-Class Classifier (QMCC), using identical numbers of layers and training epochs. Additionally, comparisons are made with well-established standard classical classifiers. Experimental results implemented on the PennyLane platform demonstrate that the proposed model achieves high test accuracies within only 10–15 training epochs, reaching 100% (Iris), 98.3% (BNA), 91.1% (Raisin), 97.0% (WIL), 99.2% (Penguin), 94.0% (Wine), and 95.4% (HTRU2). These findings indicate that the proposed ansatz effectively extracts meaningful features and performs competitively in both binary and multi-class classification tasks, highlighting its potential for practical quantum machine learning applications.
Parameterized Quantum Circuits (PQCs) with fixed structures severely degrade the performance of Quantum Machine Learning (QML). To address this, a Hybrid Quantum-Classical Classifier (HQCC) is proposed. It adaptively optimizes the PQC through a dynamic circuit generator driven by Long Short Term Memory (LSTM) and exploits architectural plasticity to balance the entanglement performance and expressiveness, opening up a practical pathway for efficiently deploying QML in the Noisy Intermediate-Scale Quantum (NISQ) era. Extensive experiments on MNIST and Fashion-MNIST demonstrate that HQCC achieves up to 99.86% accuracy in binary classification and 97.12% in multi-class tasks, surpassing state-of-the-art quantum and classical baselines.
Quantum machine learning has emerged as a promising frontier, leveraging the principles of quantum computing to enhance classical algorithms. This paper proposes an optimized Quantum Support Vector Classifier (QSVC) for the classification of the MNIST dataset (a benchmark in handwritten digit recognition). We employ a Chebyshev Parameterized Quantum Circuit (PQC) with an increased number of qubits and layers, and utilize an existing projected quantum kernel method to effectively capture the complex patterns in the data. To enhance model robustness, data augmentation techniques are applied, and dimensionality reduction is performed using Principal Component Analysis (PCA). The proposed QSVC demonstrates competitive accuracy on both the training and testing datasets, highlighting the potential of quantum kernel methods in practical machine learning applications. A comparative analysis with classical Support Vector Machines (SVM) demonstrates the feasibility of quantum methods for high-dimensional classification tasks. Additionally, we investigate the impact of varying the number of qubits in the quantum circuit, providing in-depth insights into the scalability and performance trade-offs of quantum kernel methods.
The classical-quantum interface for loading classical data into quantum systems is an indispensable component of quantum information processing, and the parameterized quantum circuit (PQC) represents significant methodology in this area. However, a challenge in designing parameterized quantum circuits that can fully utilize limited qubit resources while accurately representing classical data remains. To address this issue, we propose the enhanced natural parameterized quantum circuit (ENPQC), which achieves the maximum parameter capacity of quantum systems and preserves the local structure of the original dataset. To make the encoding circuits more experiment friendly, we further provide two near-optimal circuits that achieve near-maximum capacity and are comparable in complexity to the existing PQCs. We numerically show that the ENPQC overwhelms other encoding methods for multiple datasets, demonstrating its potential for machine learning tasks. Furthermore, we experimentally validate our scheme by demonstrating a three-class classification task on an NMR platform, which achieves over 97 % accuracy. This work provides a powerful tool for the classical-quantum interface, paving the way for quantum big data processing during the noisy intermediate-scale quantum era.
An improved quantum neural network based on a parameterized quantum circuit for 0 or 1 classification of images is designed in this paper. A classical handwritten digital image of size28×2828 \times 2828×28pixels is compressed into a4×44 \times 44×4pixel image, whose 16 classical images represent the probability amplitudes of a 4-qubit state input in the quantum state preparation circuit. The output and corresponding 0 or 1 labels are used as training data for supervised learning of a parameterized quantum recognition circuit composed of 4 qubits. The complete design process is studied in detail, including the input of classical data, quantum state preparation, the output recognition of images by the parameterized quantum circuit, and the projection measurement of the designated readout qubit. In the training of the network parameters, the goal of minimizing the loss function is to achieve optimal quantum circuit parameters. In the performance comparison experiments, handwritten digital images from the MNIST dataset are used to conduct recognition tests on two specific digits, and the test accuracy is 98.88%. The recognition accuracy rate increases by 8.13% compared with the recognition performance before the improvement. The quantum image recognition network designed in this paper can be extended to multiclass classification applications.
Quantum neural networks are a popular realization of quantum machine learning. Typically, classical data is first embedded into the state vector of a quantum system. A parameterized quantum circuit (PQC) then acts on the quantum state, with its trainable parameters continuously adjusted during the optimization process. However, current quantum hardware faces challenges, such as accumulating noise with increasing circuit complexity and a limited set of native gate operations. As a result, transpiling quantum circuits to real hardware often increases the number of the required gate instructions. These factors set considerable constraints on the accuracy of quantum machine learning models. To address these limitations, we propose a novel quantum neural network architecture, termed hardware-native parameterized quantum embedding (HN-PQE). Our approach offers two key advantages: First, HN-PQE exclusively employs the native gates of IBM's current Eagle quantum processor family, ensuring that the gate count remains stable during transpilation. Second, by combining data embedding with the PQC, HN-PQE achieves a highly compact circuit design. We empirically validate our approach on two classification tasks, simulating both idealized (no hardware noise) and noisy conditions (mimicking IBM's Brisbane device). When compared to two popular quantum neural networks, HN-PQE showed similar performance in idealized scenarios but demonstrated significant noise resilience under hardware-noise conditions. This resilience makes HN-PQE a promising candidate for future quantum machine learning experiments on real hardware.