Abstract Particle flow classification is essential in high-energy and nuclear physics. This work proposes the quantum complete graph self-attention network (QCGAT), which selects particles with high transverse momentum and uses a quantum self-attention mechanism for feature extraction. Unlike previous methods, the proposed QCGAT framework introduces a non-measurement quantum self-attention mechanism within an entangled quantum network, enabling the direct embedding of attention coefficients into quantum state amplitudes and thereby avoiding quantum-to-classical conversion. Furthermore, this work introduces a quantum distributed dimensionality reduction architecture that specifically enables tunable cross-scale data adaptation. Experiments on the Top Quark Tagging dataset show that QCGAT achieves 83.5% accuracy and 88.7% AUC, surpassing hybrid models by 1% and 0.4%. Compared with traditional quantum encoder baseline, it improves accuracy by 0.7%; when compared with traditional quantum encoder baselines having similar or fewer parameter counts, it achieves up to 1.6% higher accuracy. These results highlight the effectiveness and potential of QCGAT in quantum machine learning for particle physics.
Abstract Particle flow classification is essential in high-energy and nuclear physics. This work proposes the quantum complete graph self-attention network (QCGAT), which selects particles with high transverse momentum and uses a quantum self-attention mechanism for feature extraction. Unlike previous methods, the proposed QCGAT framework introduces a non-measurement quantum self-attention mechanism within an entangled quantum network, enabling the direct embedding of attention coefficients into quantum state amplitudes and thereby avoiding quantum-to-classical conversion. Furthermore, this work introduces a quantum distributed dimensionality reduction architecture that specifically enables tunable cross-scale data adaptation. Experiments on the Top Quark Tagging dataset show that QCGAT achieves 83.5% accuracy and 88.7% AUC, surpassing hybrid models by 1% and 0.4%. Compared with traditional quantum encoder baseline, it improves accuracy by 0.7%; when compared with traditional quantum encoder baselines having similar or fewer parameter counts, it achieves up to 1.6% higher accuracy. These results highlight the effectiveness and potential of QCGAT in quantum machine learning for particle physics.
Quantum machine learning is a promising direction for building more efficient and expressive models, particularly in domains where understanding complex, structured data is critical. We present the Quantum Graph Transformer (QGT), a hybrid graph-based architecture that integrates a quantum self-attention mechanism into the message-passing framework for structured language modeling. The attention mechanism is implemented using parameterized quantum circuits (PQCs), which enable the model to capture rich contextual relationships while significantly reducing the number of trainable parameters compared to classical attention mechanisms. We evaluate QGT on five sentiment classification benchmarks. Experimental results demonstrate that QGT effectively learns sentiment representations, achieving accuracies of 93.0%, 90.5%, and 88.0% on the Yelp, IMDB, and Amazon datasets, and 100% and 95.12% on the synthetic MC and RP datasets, respectively. These results highlight the potential of graph-based quantum NLP techniques for advancing efficient and scalable language understanding.
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.
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.
Machine learning, particularly deep neural networks, has seen widespread application in high-energy physics. Recently, quantum machine learning has emerged by integrating quantum computing with classical ML techniques. In this work, we propose the Quantum Complete Graph Neural Network (QCGNN), tailored for fully connected graphs and reducing computational complexity from O(N2) to O(N). We apply QCGNN to the jet tagging task in the datasets Top and JetNet for showing the feasibility, achieving AUCs of 0.932 and 0.822 via simulators, respectively, comparable to the leading classical models. On real quantum hardware via the IBM Quantum Platform (IBMQ), however, the AUC drops to around 0.5 due to quantum noise, indicating current devices remain impractical. The scaling behavior of QCGNN on computational complexity is further examined through runtime measurements on actual IBMQ machines.
Transformer now underpins modern AI as its core infrastructure. Its defining capability-dynamically focusing on the most relevant information in complex inputs-is bounded above by the self-attention scoring function. Quantum computing, with its superposition, entanglement, and probabilistic outputs, offers a fundamentally distinct computational framework for exploring beyond the design constraints of classical scoring functions. While quantum attention mechanisms have shown initial promise, existing works remain largely confined to redefining feature similarity measures, leaving the systematic use of parameterized quantum circuits (PQCs) as scoring functions largely unexplored; a substantial portion of existing schemes further rely on purely quantum architectures, precluding effective encoding of high-dimensional image inputs in the Noisy Intermediate-Scale Quantum era. We propose the Quantum Parameterized Self-Attention Network (QPSAN), implementing the self-attention scoring function via PQCs with only 5 trainable quantum parameters per layer. QPSAN computes query-key attention scores through quantum state encoding and joint measurement, yielding naturally bounded outputs without the explicit scaling of classical dot-product attention. We further establish a theoretical framework of the mathematical properties of this scoring function, demonstrating its potential to capture complex nonlinear query-key interactions, and quantifying the structural constraints of the encoding layer via effective degrees of freedom analysis. Experiments on four vision datasets show that QPSAN significantly outperforms the Vision Transformer (ViT) baseline, with the quantum representational advantage amplifying as data complexity increases. Ablation studies indicate that the performance gains may stem from the structural inductive bias of the quantum circuit rather than from parameter scale.
Machine learning, particularly deep neural networks, has seen widespread application in high-energy physics. Recently, quantum machine learning has emerged by integrating quantum computing with classical ML techniques. In this work, we propose the Quantum Complete Graph Neural Network (QCGNN), tailored for fully connected graphs and reducing computational complexity from O(N2) to O(N). We apply QCGNN to the jet tagging task in the datasets Top and JetNet for showing the feasibility, achieving AUCs of 0.932 and 0.822 via simulators, respectively, comparable to the leading classical models. On real quantum hardware via the IBM Quantum Platform (IBMQ), however, the AUC drops to around 0.5 due to quantum noise, indicating current devices remain impractical. The scaling behavior of QCGNN on computational complexity is further examined through runtime measurements on actual IBMQ machines.