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:2404.17378

Quantum Adjoint Convolutional Layers for Effective Data Representation

Ren-Xin Zhao, Shi Wang, Yaonan Wang

Published Apr 26, 2024• 3 citations
arXivHTMLPDF

Abstract

Quantum Convolutional Layer (QCL) is considered as one of the core of Quantum Convolutional Neural Networks (QCNNs) due to its efficient data feature extraction capability. However, the current principle of QCL is not as mathematically understandable as Classical Convolutional Layer (CCL) due to its black-box structure. Moreover, classical data mapping in many QCLs is inefficient. To this end, firstly, the Quantum Adjoint Convolution Operation (QACO) consisting of a quantum amplitude encoding and its inverse is theoretically shown to be equivalent to the quantum normalization of the convolution operation based on the Frobenius inner product while achieving an efficient characterization of the data. Subsequently, QACO is extended into a Quantum Adjoint Convolutional Layer (QACL) by Quantum Phase Estimation (QPE) to compute all Frobenius inner products in parallel. At last, comparative simulation experiments are carried out on PennyLane and TensorFlow platforms, mainly for the two cases of kernel fixed and unfixed in QACL. The results demonstrate that QACL with the insight of special quantum properties for the same images, provides higher training accuracy in MNIST and Fashion MNIST classification experiments, but sacrifices the learning performance to some extent. Predictably, our research lays the foundation for the development of efficient and interpretable quantum convolutional networks and also advances the field of quantum machine vision.

DOI
10.48550/arxiv.2404.17378

Related papers

An Interpretable Quantum Adjoint Convolutional Layer for Image Classification

Shi Wang, Mengyi Wang, Ren-Xin Zhao +2 more

The interpretability of quantum machine learning (QML) refers to the capability to provide clear and understandable explanations for the predictions and decision-making processes of QML models. However, most quantum convolutional layers (QCLs) utilize closed-box structures that are inherently devoid of interpretability, leading to the opacity of principles and the suboptimal mapping of classical data. This significantly undermines the reliability of QML models. In addition, most of the current QML interpretability focuses on post hoc interpretability seriously neglecting the importance of exploring intrinsic causes. To tackle these challenges, we introduce the quantum adjoint convolution operation (QACO). It is an intrinsic interpretability scheme based on quantum evolution, as its quantum mapping precisely corresponds to the position and pixel values of the image and its principle is equivalent to the Frobenius inner product (FIP). Furthermore, we extend the QACO concept into the quantum adjoint convolutional layer (QACL) by integrating the quantum phase estimation (QPE) algorithm, enabling the parallel computation of all FIPs. Experimental results on PennyLane and TensorFlow platforms demonstrate that our method achieves a 6.3%, 3.4%, and 2.9% higher average test accuracy on Fashion MNIST, MNIST, and DermaMNIST datasets compared to classical and uninterpretable quantum counterparts, respectively, while maintaining 73.3% noise-robust accuracy under Gaussian noise, showcasing its superior generalizability and resilience in practical scenarios.

IEEE Transactions on Cybernetics•May 22, 2025•5 citations

A Tutorial on Quantum Convolutional Neural Networks (QCNN)

Seunghyeok Oh, Jaeho Choi, Joongheon Kim

Convolutional Neural Network (CNN) is a popular model in computer vision and has the advantage of making good use of the correlation information of data. However, CNN is challenging to learn efficiently if the given dimension of data or model becomes too large. Quantum Convolutional Neural Network (QCNN) provides a new solution to a problem to solve with CNN using a quantum computing environment, or a direction to improve the performance of an existing learning model. The first study to be introduced proposes a model to effectively solve the classification problem in quantum physics and chemistry by applying the structure of CNN to the quantum computing environment. The research also proposes the model that can be calculated with O(log(n)) depth using Multi-scale Entanglement Renormalization Ansatz (MERA). The second study introduces a method to improve the model's performance by adding a layer using quantum computing to the CNN learning model used in the existing computer vision. This model can also be used in small quantum computers, and a hybrid learning model can be designed by adding a quantum convolution layer to the CNN model or replacing it with a convolution layer. This paper also verifies whether the QCNN model is capable of efficient learning compared to CNN through training using the MNIST dataset through the TensorFlow Quantum platform.

arXiv:2009.09423•International Conference on Information and Communication Technology Convergence (ICTC)•Oct 21, 2020•184 citations

Quantum resource-performance balance in quantum convolutional neural networks: a study of hierarchical Ansatz-based QCNN

Zihao Liu, Chengyong Zheng, Huiping Zheng +1 more

Abstract Quantum Convolutional Neural Networks (QCNNs) are a significant quantum machine learning architecture. However, most current designs still mimic the ‘convolution-pooling’ structure of classical CNNs, facing dual challenges of limited feature extraction and inefficient quantum resource usage. To address this, we propose a QCNN based on a hierarchical Ansatz design. Its core is an alternating ‘convolution-entanglement’ structure, which replaces abrupt qubit discarding in traditional pooling with sequential global entanglement layers. This enables non-destructive directional information aggregation, aiming to preserve quantum correlations in data more comprehensively. In the encoding layer, we integrate Principal Component Analysis (PCA) with Instantaneous Quantum Polynomial (IQP) encoding to mitigate the dimensionality mismatch between high-dimensional classical data and limited quantum resources. To systematically evaluate the performance of the proposed architecture, we conducted extensive experiments on the MNIST and Fashion-MNIST datasets. The results demonstrate that: 1) Under various convolutional kernel configurations, our model achieves excellent classification performance, peaking at 99.39% accuracy on MNIST; 2) Even with minimalistic single-qubit rotation gates as the convolutional layer, the model attains 99.14% accuracy using only 16 parameters, demonstrating high parameter efficiency; 3) Crucially, experiments reveal a nonlinear relationship between quantum resources and performance. When qubits exceed a task-specific optimal number, performance declines significantly due to feature space dilution and exacerbated Barren Plateaus. This suggests that, under current quantum hardware conditions, matching resource allocation to task complexity may be more critical than simply scaling up the system. This study offers one potential direction for exploring QCNN architectures. The findings still require further validation across more diverse tasks and in quantum hardware environments closer to practical conditions. We hope this work can provide some useful insights and inform subsequent research.

Physica Scripta•Mar 13, 2026•0 citations

A Parallel Quantum Feature Encoding Scheme for Effective Classical Data Classification in Quantum Convolutional Neural Networks

Raisa Mashtura, Jishnu Mahmud, Shaikh Anowarul Fattah +1 more

Quantum machine learning is one of the most exciting new avenues in the world of artificial intelligence, especially because of the enormous computational power of quantum computers and the promise of the development of near error-free quantum computers in the not-so-distant future. For quantum algorithms to be used in real-life applications, quantum computers must be able to work with classical data. One of the key steps in quantum algorithms dealing with classical data is the encoding of classical data points to quantum states, which can then be processed by quantum gates. It is known that the type of encoding technique that works best for a particular network is dependent on the dataset being used. In this paper, a new parallel structure is proposed utilizing two encoding techniques, namely amplitude encoding and angle encoding, for effective classical data classification via quantum neural network. The paper further proposes a maximally expressible and entangled ansatz used to design a simple Quantum Convolutional Neural Network (QCNN) with only 32 parameters, that is used in the latter stages of the network and is kept the same across all encoding instances so that a comparison between the different encoding methods is possible. Extensive experimentation is carried out on two publicly available image datasets, namely MNIST and Fashion MNIST. The results show that the proposed method achieves better results than any of the encoding techniques deployed alone for binary classification.

IEEE Region 10 Conference (TENCON)•Oct 31, 2023•4 citations

Quantum Convolutional Neural Networks for Visual Pattern Recognition

Niroji Thayalan, Vinayagamoorthy Balalojanan, Vithiyasahar Vigneswaran +4 more

Quantum machine learning is emerging as a promising frontier at the intersection of quantum computing and Artificial Intelligence, offering potential gains in speed, efficiency, and robustness. In this paper, a hybrid Quantum Convolutional Neural Network (QCNN) architecture is presented for visual pattern recognition tasks, leveraging quantum superposition and entanglement for enhanced feature extraction. Unlike previous studies that focus on small-scale or simplified datasets, this study systematically evaluates QCNNs across multiple benchmark datasets and provides a direct comparison with classical CNNs, highlighting practical quantum advantages such as parameter efficiency and noise-resilience. The proposed approach encodes classical image data from benchmark datasets, including$70 ~\mathrm{K} 28 \times 28$grayscale images from MNIST and FashionMNIST, and$\mathbf{6 0 K}$downsampled grayscale CIFAR-10 images, into quantum states using amplitude encoding, followed by hierarchical quantum convolution and pooling layers implemented via parametrised quantum circuits (PQCs). The model culminates in a classical dense layer for final classification. Experimental results demonstrate that the QCNN achieves competitive performance on low-dimensional grayscale datasets with 93.2 % accuracy on MNIST and 88.5% on Fashion MNIST, though it underperforms on more complex datasets like CIFAR-10 with 67.8 % accuracy due to current quantum hardware limitations. While not yet surpassing classical CNNs in raw accuracy, the proposed QCNN exhibits notable parameter efficiency, noise resilience, and theoretical potential for energy-efficient computation, highlighting its promise for future applications as quantum technologies mature.

International Conference on Advanced Research in Computing (ICARC)•Feb 18, 2026•1 citation

The inherent convolution property of quantum neural networks

Zhimin Wang, Guoxin Qu, Guoqiang Zhong +1 more

Abstract Quantum neural networks (QNNs) represent a pioneering intersection of quantum computing and deep learning. In this study, we unveil a fundamental convolution property inherent to QNNs, stemming from the natural parallelism of quantum gate operations on quantum states. Notably, QNNs are capable of performing a convolutional layer using a single quantum gate, whereas classical methods require $2^n$ basic operations. This essential property has been largely overlooked in the design of existing quantum convolutional neural networks (QCNNs), limiting their ability to capture key structural features of classical CNNs, including local connectivity, parameter sharing, and multi-channel, multi-layer architectures. To address these limitations, we propose novel QCNN architectures that explicitly harness the convolutional nature of QNNs. We validate the effectiveness of these architectures through extensive numerical experiments focused on multiclass image classification. Our findings provide deep insights into the realization of convolutional mechanisms within QNNs, marking a substantial advancement in the development of QCNNs and broadening their potential for efficient data processing.

arXiv:2504.08487•Apr 2, 2025•2 citations
Quantum Convolutional Layer (QCL) is considered as one of the core of Quantum Convolutional Neural Networks (QCNNs) due to its efficient data feature extraction capability. However, the current principle of QCL is not as mathematically understandable as Classical Convolutional Layer (CCL) due to its black-box structure. Moreover, classical data mapping in many QCLs is inefficient. To this end, firstly, the Quantum Adjoint Convolution Operation (QACO) consisting of a quantum amplitude encoding and its inverse is theoretically shown to be equivalent to the quantum normalization of the convolution operation based on the Frobenius inner product while achieving an efficient characterization of the data. Subsequently, QACO is extended into a Quantum Adjoint Convolutional Layer (QACL) by Quantum Phase Estimation (QPE) to compute all Frobenius inner products in parallel. At last, comparative simulation experiments are carried out on PennyLane and TensorFlow platforms, mainly for the two cases of kernel fixed and unfixed in QACL. The results demonstrate that QACL with the insight of special quantum properties for the same images, provides higher training accuracy in MNIST and Fashion MNIST classification experiments, but sacrifices the learning performance to some extent. Predictably, our research lays the foundation for the development of efficient and interpretable quantum convolutional networks and also advances the field of quantum machine vision.
The interpretability of quantum machine learning (QML) refers to the capability to provide clear and understandable explanations for the predictions and decision-making processes of QML models. However, most quantum convolutional layers (QCLs) utilize closed-box structures that are inherently devoid of interpretability, leading to the opacity of principles and the suboptimal mapping of classical data. This significantly undermines the reliability of QML models. In addition, most of the current QML interpretability focuses on post hoc interpretability seriously neglecting the importance of exploring intrinsic causes. To tackle these challenges, we introduce the quantum adjoint convolution operation (QACO). It is an intrinsic interpretability scheme based on quantum evolution, as its quantum mapping precisely corresponds to the position and pixel values of the image and its principle is equivalent to the Frobenius inner product (FIP). Furthermore, we extend the QACO concept into the quantum adjoint convolutional layer (QACL) by integrating the quantum phase estimation (QPE) algorithm, enabling the parallel computation of all FIPs. Experimental results on PennyLane and TensorFlow platforms demonstrate that our method achieves a 6.3%, 3.4%, and 2.9% higher average test accuracy on Fashion MNIST, MNIST, and DermaMNIST datasets compared to classical and uninterpretable quantum counterparts, respectively, while maintaining 73.3% noise-robust accuracy under Gaussian noise, showcasing its superior generalizability and resilience in practical scenarios.
Convolutional Neural Network (CNN) is a popular model in computer vision and has the advantage of making good use of the correlation information of data. However, CNN is challenging to learn efficiently if the given dimension of data or model becomes too large. Quantum Convolutional Neural Network (QCNN) provides a new solution to a problem to solve with CNN using a quantum computing environment, or a direction to improve the performance of an existing learning model. The first study to be introduced proposes a model to effectively solve the classification problem in quantum physics and chemistry by applying the structure of CNN to the quantum computing environment. The research also proposes the model that can be calculated with O(log(n)) depth using Multi-scale Entanglement Renormalization Ansatz (MERA). The second study introduces a method to improve the model's performance by adding a layer using quantum computing to the CNN learning model used in the existing computer vision. This model can also be used in small quantum computers, and a hybrid learning model can be designed by adding a quantum convolution layer to the CNN model or replacing it with a convolution layer. This paper also verifies whether the QCNN model is capable of efficient learning compared to CNN through training using the MNIST dataset through the TensorFlow Quantum platform.
Abstract Quantum Convolutional Neural Networks (QCNNs) are a significant quantum machine learning architecture. However, most current designs still mimic the ‘convolution-pooling’ structure of classical CNNs, facing dual challenges of limited feature extraction and inefficient quantum resource usage. To address this, we propose a QCNN based on a hierarchical Ansatz design. Its core is an alternating ‘convolution-entanglement’ structure, which replaces abrupt qubit discarding in traditional pooling with sequential global entanglement layers. This enables non-destructive directional information aggregation, aiming to preserve quantum correlations in data more comprehensively. In the encoding layer, we integrate Principal Component Analysis (PCA) with Instantaneous Quantum Polynomial (IQP) encoding to mitigate the dimensionality mismatch between high-dimensional classical data and limited quantum resources. To systematically evaluate the performance of the proposed architecture, we conducted extensive experiments on the MNIST and Fashion-MNIST datasets. The results demonstrate that: 1) Under various convolutional kernel configurations, our model achieves excellent classification performance, peaking at 99.39% accuracy on MNIST; 2) Even with minimalistic single-qubit rotation gates as the convolutional layer, the model attains 99.14% accuracy using only 16 parameters, demonstrating high parameter efficiency; 3) Crucially, experiments reveal a nonlinear relationship between quantum resources and performance. When qubits exceed a task-specific optimal number, performance declines significantly due to feature space dilution and exacerbated Barren Plateaus. This suggests that, under current quantum hardware conditions, matching resource allocation to task complexity may be more critical than simply scaling up the system. This study offers one potential direction for exploring QCNN architectures. The findings still require further validation across more diverse tasks and in quantum hardware environments closer to practical conditions. We hope this work can provide some useful insights and inform subsequent research.
Quantum machine learning is one of the most exciting new avenues in the world of artificial intelligence, especially because of the enormous computational power of quantum computers and the promise of the development of near error-free quantum computers in the not-so-distant future. For quantum algorithms to be used in real-life applications, quantum computers must be able to work with classical data. One of the key steps in quantum algorithms dealing with classical data is the encoding of classical data points to quantum states, which can then be processed by quantum gates. It is known that the type of encoding technique that works best for a particular network is dependent on the dataset being used. In this paper, a new parallel structure is proposed utilizing two encoding techniques, namely amplitude encoding and angle encoding, for effective classical data classification via quantum neural network. The paper further proposes a maximally expressible and entangled ansatz used to design a simple Quantum Convolutional Neural Network (QCNN) with only 32 parameters, that is used in the latter stages of the network and is kept the same across all encoding instances so that a comparison between the different encoding methods is possible. Extensive experimentation is carried out on two publicly available image datasets, namely MNIST and Fashion MNIST. The results show that the proposed method achieves better results than any of the encoding techniques deployed alone for binary classification.
Quantum machine learning is emerging as a promising frontier at the intersection of quantum computing and Artificial Intelligence, offering potential gains in speed, efficiency, and robustness. In this paper, a hybrid Quantum Convolutional Neural Network (QCNN) architecture is presented for visual pattern recognition tasks, leveraging quantum superposition and entanglement for enhanced feature extraction. Unlike previous studies that focus on small-scale or simplified datasets, this study systematically evaluates QCNNs across multiple benchmark datasets and provides a direct comparison with classical CNNs, highlighting practical quantum advantages such as parameter efficiency and noise-resilience. The proposed approach encodes classical image data from benchmark datasets, including70 K28×2870 ~\mathrm{K} 28 \times 2870 K28×28grayscale images from MNIST and FashionMNIST, and60K\mathbf{6 0 K}60Kdownsampled grayscale CIFAR-10 images, into quantum states using amplitude encoding, followed by hierarchical quantum convolution and pooling layers implemented via parametrised quantum circuits (PQCs). The model culminates in a classical dense layer for final classification. Experimental results demonstrate that the QCNN achieves competitive performance on low-dimensional grayscale datasets with 93.2 % accuracy on MNIST and 88.5% on Fashion MNIST, though it underperforms on more complex datasets like CIFAR-10 with 67.8 % accuracy due to current quantum hardware limitations. While not yet surpassing classical CNNs in raw accuracy, the proposed QCNN exhibits notable parameter efficiency, noise resilience, and theoretical potential for energy-efficient computation, highlighting its promise for future applications as quantum technologies mature.
Abstract Quantum neural networks (QNNs) represent a pioneering intersection of quantum computing and deep learning. In this study, we unveil a fundamental convolution property inherent to QNNs, stemming from the natural parallelism of quantum gate operations on quantum states. Notably, QNNs are capable of performing a convolutional layer using a single quantum gate, whereas classical methods require 2n2^n2n basic operations. This essential property has been largely overlooked in the design of existing quantum convolutional neural networks (QCNNs), limiting their ability to capture key structural features of classical CNNs, including local connectivity, parameter sharing, and multi-channel, multi-layer architectures. To address these limitations, we propose novel QCNN architectures that explicitly harness the convolutional nature of QNNs. We validate the effectiveness of these architectures through extensive numerical experiments focused on multiclass image classification. Our findings provide deep insights into the realization of convolutional mechanisms within QNNs, marking a substantial advancement in the development of QCNNs and broadening their potential for efficient data processing.