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:2401.14089

GQHAN: A Grover-inspired Quantum Hard Attention Network

Ren-Xin Zhao, Jinjing Shi, Xuelong Li

Published Jan 25, 2024• 6 citations
arXivHTMLPDF

Abstract

Numerous current Quantum Machine Learning (QML) models exhibit an inadequacy in discerning the significance of quantum data, resulting in diminished efficacy when handling extensive quantum datasets. Hard Attention Mechanism (HAM), anticipated to efficiently tackle the above QML bottlenecks, encounters the substantial challenge of non-differentiability, consequently constraining its extensive applicability. In response to the dilemma of HAM and QML, a Grover-inspired Quantum Hard Attention Mechanism (GQHAM) consisting of a Flexible Oracle (FO) and an Adaptive Diffusion Operator (ADO) is proposed. Notably, the FO is designed to surmount the non-differentiable issue by executing the activation or masking of Discrete Primitives (DPs) with Flexible Control (FC) to weave various discrete destinies. Based on this, such discrete choice can be visualized with a specially defined Quantum Hard Attention Score (QHAS). Furthermore, a trainable ADO is devised to boost the generality and flexibility of GQHAM. At last, a Grover-inspired Quantum Hard Attention Network (GQHAN) based on QGHAM is constructed on PennyLane platform for Fashion MNIST binary classification. Experimental findings demonstrate that GQHAN adeptly surmounts the non-differentiability hurdle, surpassing the efficacy of extant quantum soft self-attention mechanisms in accuracies and learning ability. In noise experiments, GQHAN is robuster to bit-flip noise in accuracy and amplitude damping noise in learning performance. Predictably, the proposal of GQHAN enriches the Quantum Attention Mechanism (QAM), lays the foundation for future quantum computers to process large-scale data, and promotes the development of quantum computer vision.

DOI
10.48550/arxiv.2401.14089

Related papers

QSAN: A Near-Term Achievable Quantum Self-Attention Network

Jinjing Shi, Ren-Xin Zhao, Wenxuan Wang +2 more

Self-attention mechanism (SAM) is good at capturing the intrinsic connection between features to dramatically boost the performance of machine learning models. Nevertheless, the capability of SAM is not equipped with many current quantum machine learning (QML) models, thus confining their expansion on massive high-dimensional quantum data. To address the above problems, a quantum SAM (QSAM) consisting of a quantum logic similarity (QLS)-based quantum bit self-attention score matrix (QBSASM) is introduced to augment the data representation of SAM exponentially. According to QSAM, the framework and quantum circuits of a one-step achievable quantum self-attention network (QSAN) are designed to consider measurement times compression fully. Moreover, a prototype of quantum coordinates is presented during the design process to describe the mathematical relationship between the output bits and the control bits to facilitate the programming. Ultimately, MNIST binary classification experiments on the PennyLane platform and comparisons with cutting-edge QML models demonstrate QSAN converges about $1.7\times $ and $2.3\times $ faster than hardware-efficient ansatz and quantum approximate optimization algorithm (QAOA) ansatz, respectively, with similar parameter configurations and 100% prediction accuracy, which indicates that it has a better learning capability. In the CIFAR-10 classification experiments, QSAN achieves high prediction accuracy at a small scale relative to classical machine learning models. Predictably, QSAN elevates the efficiency of QML models and lays the foundation for future quantum computers to perform machine learning on massive amounts of data while promoting the advancement of quantum computer vision and other fields.

arXiv:2207.07563•IEEE Transactions on Neural Networks and Learning Systems•Dec 16, 2024•41 citations

QAHAN: A Quantum Annealing Hard Attention Network

Ren-Xin Zhao

Hard Attention Mechanisms (HAMs) effectively filter essential information discretely and significantly boost the performance of machine learning models on large datasets. Nevertheless, they confront the challenge of non-differentiability, which raises the risk of convergence to a local optimum. Quantum Annealing (QA) is expected to solve the above dilemma. We propose a Quantum Annealing Hard Attention Mechanism (QAHAM) for faster convergence to the global optimum without the need to compute gradients by exploiting the quantum tunneling effect. Based on the above theory, we construct a Quantum Annealing Hard Attention Network (QAHAN) on D-Wave and Pytorch platforms for MNIST and CIFAR-10 multi-classification. Experimental results indicate that the QAHAN converges faster, exhibits smoother accuracy and loss curves, and demonstrates superior noise robustness compared to two traditional HAMs. Predictably, our scheme accelerates the convergence between the fields of quantum algorithms and machine learning, while advancing the field of quantum machine vision.

arXiv:2412.20930•Dec 30, 2024•3 citations

QKSAN: A Quantum Kernel Self-Attention Network

Ren-Xin Zhao, Jinjing Shi, Xuelong Li

The Self-Attention Mechanism (SAM) excels at distilling important information from the interior of data to improve the computational efficiency of models. Nevertheless, many Quantum Machine Learning (QML) models lack the ability to distinguish the intrinsic connections of information like SAM, which limits their effectiveness on massive high-dimensional quantum data. To tackle the above issue, a Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. Further, a Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques to release half of quantum resources by mid-circuit measurement, thereby bolstering both feasibility and adaptability. Simultaneously, the Quantum Kernel Self-Attention Score (QKSAS) with an exponentially large characterization space is spawned to accommodate more information and determine the measurement conditions. Eventually, four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST, where the QKSAS tests and correlation assessments between noise immunity and learning ability are executed on the best-performing sub-model. The paramount experimental finding is that the QKSAN subclasses possess the potential learning advantage of acquiring impressive accuracies exceeding 98.05% with far fewer parameters than classical machine learning models. Predictably, QKSAN lays the foundation for future quantum computers to perform machine learning on massive amounts of data while driving advances in areas such as quantum computer vision.

arXiv:2308.13422•IEEE Transactions on Pattern Analysis and Machine Intelligence•Jul 29, 2024•80 citations

Quantum Machine Learning: A Novel Non-Linear Attention Mechanism

Jincheng Zhang

Quantum Machine Learning (QML) represents a paradigm shift in machine learning, leveraging the principles of quantum mechanics to enhance computational power and solve problems intractable for classical algorithms. This paper introduces a novel non-linear attention mechanism designed to improve the learning of complex data relationships and enhance the generalization ability of machine learning models. The proposed method utilizes quantum entanglement and superposition to create a mechanism capable of capturing intricate dependencies within data, offering a significant advancement over traditional attention mechanisms. The core claim of this research is that the developed quantum attention mechanism will outperform existing approaches on various benchmark datasets, demonstrating improved performance in tasks requiring complex non-linear relationships. This work explores the potential of incorporating quantum properties into the attention process, paving the way for novel machine learning algorithms with enhanced robustness and adaptability.

•Sep 3, 2026•0 citations

Quantum Machine Learning in Adaptive Attention Mechanisms

Jincheng Zhang

Quantum Machine Learning (QML) is a rapidly developing field that explores the potential of quantum computers to enhance machine learning algorithms. A critical challenge in QML is the design of efficient and effective attention mechanisms, which are fundamental to many deep learning architectures, particularly in natural language processing and computer vision. This paper investigates the application of adaptive attention mechanisms within the context of QML, specifically focusing on the design of a novel self-adaptive attention mechanism leveraging quantum properties. We propose a framework that dynamically adjusts the attention weights based on the quantum state, allowing for a more nuanced and efficient modeling process. The core claim is that this design will result in improved model performance and enhanced learning efficiency compared to traditional attention mechanisms, utilizing the inherent advantages of quantum computing. This work presents a theoretical analysis and preliminary implementation of this novel approach.

•Sep 1, 2026•0 citations

Adaptive Attention Mechanism for Quantum Machine Learning

Jincheng Zhang

Quantum machine learning (QML) offers the potential to revolutionize various fields, including drug discovery, materials science, and financial modeling, by leveraging the unique capabilities of quantum systems. However, the development of effective QML algorithms often faces challenges related to computational complexity and the need for sophisticated training strategies. This paper investigates a novel attention mechanism designed specifically for quantum machine learning, aiming to address these challenges by dynamically adjusting attention weights based on input data characteristics. We propose a framework that adapts to the data's nuances, enhancing model robustness and performance. This mechanism will be tested against various quantum machine learning tasks, demonstrating its effectiveness through illustrative examples. The core focus is on achieving a higher level of data capture and improved model generalization.

•Sep 4, 2026•0 citations
Numerous current Quantum Machine Learning (QML) models exhibit an inadequacy in discerning the significance of quantum data, resulting in diminished efficacy when handling extensive quantum datasets. Hard Attention Mechanism (HAM), anticipated to efficiently tackle the above QML bottlenecks, encounters the substantial challenge of non-differentiability, consequently constraining its extensive applicability. In response to the dilemma of HAM and QML, a Grover-inspired Quantum Hard Attention Mechanism (GQHAM) consisting of a Flexible Oracle (FO) and an Adaptive Diffusion Operator (ADO) is proposed. Notably, the FO is designed to surmount the non-differentiable issue by executing the activation or masking of Discrete Primitives (DPs) with Flexible Control (FC) to weave various discrete destinies. Based on this, such discrete choice can be visualized with a specially defined Quantum Hard Attention Score (QHAS). Furthermore, a trainable ADO is devised to boost the generality and flexibility of GQHAM. At last, a Grover-inspired Quantum Hard Attention Network (GQHAN) based on QGHAM is constructed on PennyLane platform for Fashion MNIST binary classification. Experimental findings demonstrate that GQHAN adeptly surmounts the non-differentiability hurdle, surpassing the efficacy of extant quantum soft self-attention mechanisms in accuracies and learning ability. In noise experiments, GQHAN is robuster to bit-flip noise in accuracy and amplitude damping noise in learning performance. Predictably, the proposal of GQHAN enriches the Quantum Attention Mechanism (QAM), lays the foundation for future quantum computers to process large-scale data, and promotes the development of quantum computer vision.
Self-attention mechanism (SAM) is good at capturing the intrinsic connection between features to dramatically boost the performance of machine learning models. Nevertheless, the capability of SAM is not equipped with many current quantum machine learning (QML) models, thus confining their expansion on massive high-dimensional quantum data. To address the above problems, a quantum SAM (QSAM) consisting of a quantum logic similarity (QLS)-based quantum bit self-attention score matrix (QBSASM) is introduced to augment the data representation of SAM exponentially. According to QSAM, the framework and quantum circuits of a one-step achievable quantum self-attention network (QSAN) are designed to consider measurement times compression fully. Moreover, a prototype of quantum coordinates is presented during the design process to describe the mathematical relationship between the output bits and the control bits to facilitate the programming. Ultimately, MNIST binary classification experiments on the PennyLane platform and comparisons with cutting-edge QML models demonstrate QSAN converges about $1.7\times $ and $2.3\times $ faster than hardware-efficient ansatz and quantum approximate optimization algorithm (QAOA) ansatz, respectively, with similar parameter configurations and 100% prediction accuracy, which indicates that it has a better learning capability. In the CIFAR-10 classification experiments, QSAN achieves high prediction accuracy at a small scale relative to classical machine learning models. Predictably, QSAN elevates the efficiency of QML models and lays the foundation for future quantum computers to perform machine learning on massive amounts of data while promoting the advancement of quantum computer vision and other fields.
Hard Attention Mechanisms (HAMs) effectively filter essential information discretely and significantly boost the performance of machine learning models on large datasets. Nevertheless, they confront the challenge of non-differentiability, which raises the risk of convergence to a local optimum. Quantum Annealing (QA) is expected to solve the above dilemma. We propose a Quantum Annealing Hard Attention Mechanism (QAHAM) for faster convergence to the global optimum without the need to compute gradients by exploiting the quantum tunneling effect. Based on the above theory, we construct a Quantum Annealing Hard Attention Network (QAHAN) on D-Wave and Pytorch platforms for MNIST and CIFAR-10 multi-classification. Experimental results indicate that the QAHAN converges faster, exhibits smoother accuracy and loss curves, and demonstrates superior noise robustness compared to two traditional HAMs. Predictably, our scheme accelerates the convergence between the fields of quantum algorithms and machine learning, while advancing the field of quantum machine vision.
The Self-Attention Mechanism (SAM) excels at distilling important information from the interior of data to improve the computational efficiency of models. Nevertheless, many Quantum Machine Learning (QML) models lack the ability to distinguish the intrinsic connections of information like SAM, which limits their effectiveness on massive high-dimensional quantum data. To tackle the above issue, a Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. Further, a Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques to release half of quantum resources by mid-circuit measurement, thereby bolstering both feasibility and adaptability. Simultaneously, the Quantum Kernel Self-Attention Score (QKSAS) with an exponentially large characterization space is spawned to accommodate more information and determine the measurement conditions. Eventually, four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST, where the QKSAS tests and correlation assessments between noise immunity and learning ability are executed on the best-performing sub-model. The paramount experimental finding is that the QKSAN subclasses possess the potential learning advantage of acquiring impressive accuracies exceeding 98.05% with far fewer parameters than classical machine learning models. Predictably, QKSAN lays the foundation for future quantum computers to perform machine learning on massive amounts of data while driving advances in areas such as quantum computer vision.
Quantum Machine Learning (QML) represents a paradigm shift in machine learning, leveraging the principles of quantum mechanics to enhance computational power and solve problems intractable for classical algorithms. This paper introduces a novel non-linear attention mechanism designed to improve the learning of complex data relationships and enhance the generalization ability of machine learning models. The proposed method utilizes quantum entanglement and superposition to create a mechanism capable of capturing intricate dependencies within data, offering a significant advancement over traditional attention mechanisms. The core claim of this research is that the developed quantum attention mechanism will outperform existing approaches on various benchmark datasets, demonstrating improved performance in tasks requiring complex non-linear relationships. This work explores the potential of incorporating quantum properties into the attention process, paving the way for novel machine learning algorithms with enhanced robustness and adaptability.
Quantum Machine Learning (QML) is a rapidly developing field that explores the potential of quantum computers to enhance machine learning algorithms. A critical challenge in QML is the design of efficient and effective attention mechanisms, which are fundamental to many deep learning architectures, particularly in natural language processing and computer vision. This paper investigates the application of adaptive attention mechanisms within the context of QML, specifically focusing on the design of a novel self-adaptive attention mechanism leveraging quantum properties. We propose a framework that dynamically adjusts the attention weights based on the quantum state, allowing for a more nuanced and efficient modeling process. The core claim is that this design will result in improved model performance and enhanced learning efficiency compared to traditional attention mechanisms, utilizing the inherent advantages of quantum computing. This work presents a theoretical analysis and preliminary implementation of this novel approach.
Quantum machine learning (QML) offers the potential to revolutionize various fields, including drug discovery, materials science, and financial modeling, by leveraging the unique capabilities of quantum systems. However, the development of effective QML algorithms often faces challenges related to computational complexity and the need for sophisticated training strategies. This paper investigates a novel attention mechanism designed specifically for quantum machine learning, aiming to address these challenges by dynamically adjusting attention weights based on input data characteristics. We propose a framework that adapts to the data's nuances, enhancing model robustness and performance. This mechanism will be tested against various quantum machine learning tasks, demonstrating its effectiveness through illustrative examples. The core focus is on achieving a higher level of data capture and improved model generalization.