Quantum Parameterized Self-Attention Network for Image Classification

• URL: http://arxiv.org/abs/2605.25365v1
• Date: Mon, 25 May 2026 02:44:13 GMT
• Title: Quantum Parameterized Self-Attention Network for Image Classification
• Abstract summary: We propose a quantum-based self-attention scoring function.<n>We show that it can capture complex nonlinear query-key interactions, and quantifying the structural constraints of the encoding layer.<n> Experiments on four vision datasets show that QPSAN significantly outperforms the Vision Transformer (ViT) baseline.
• Score: 27.317371900372127
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Breaking the Curse of Dimensionality in Quantum PDE Solvers via Gevrey Regularity [4.219859693008517]
  We use the Gevrey hierarchy to stratifies the space between smooth and analytic functions.<n>We show how our Fourier methods do so efficiently at varying target precisions on a quantum computer.<n>As an application, we introduce a hierarchy of many-body quantum simulation pipelines.
  arXiv  Detail & Related papers  (2026-08-08T03:40:25Z)
• AQER: a scalable and efficient data loader for digital quantum computers [62.40228216126285]
  We develop AQER, a scalable AQL method that constructs the loading circuit by systematically reducing entanglement in target states.<n>We conduct systematic experiments to evaluate the effectiveness of AQER, using synthetic datasets, classical image and language datasets, and a quantum many-body state datasets with up to 50 qubits.
  arXiv  Detail & Related papers  (2026-02-02T14:39:42Z)
• Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning [0.0]
  Quantum Graph Attention Network (QGAT) is a hybrid graph neural network that integrates variational quantum circuits into the attention mechanism.<n>We show QGAT's effectiveness in capturing complex structural dependencies and improved generalization in inductive scenarios.<n>Experiments confirm that quantum embedding enhances robustness against feature and structural noise, suggesting advantages in handling real-world noisy data.
  arXiv  Detail & Related papers  (2025-08-25T03:25:48Z)
• VQC-MLPNet: An Unconventional Hybrid Quantum-Classical Architecture for Scalable and Robust Quantum Machine Learning [50.95799256262098]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning but face challenges in expressivity, trainability, and noise resilience.<n>We propose VQC-MLPNet, a hybrid architecture where a VQC generates the first-layer weights of a classical multilayer perceptron during training, while inference is performed entirely classically.
  arXiv  Detail & Related papers  (2025-06-12T01:38:15Z)
• QAMA: Scalable Quantum Annealing Multi-Head Attention Operator for Deep Learning [48.12231190677108]
  Quantum Annealing Multi-Head Attention (QAMA) is proposed, a novel drop-in operator that reformulates attention as an energy-based Hamiltonian optimization problem.<n>In this framework, token interactions are encoded into binary quadratic terms, and quantum annealing is employed to search for low-energy configurations.<n> Empirically, evaluation on both natural language and vision benchmarks shows that, across tasks, accuracy deviates by at most 2.7 points from standard multi-head attention.
  arXiv  Detail & Related papers  (2025-04-15T11:29:09Z)
• Quantum parallel information exchange (QPIE) hybrid network with transfer learning [18.43273756128771]
  Quantum machine learning (QML) has emerged as an innovative framework with the potential to uncover complex patterns.<n>We introduce quantum parallel information exchange (QPIE) hybrid network, a new non-sequential hybrid classical quantum model architecture.<n>We develop a dynamic gradient selection method that applies the parameter shift rule on quantum processing units.
  arXiv  Detail & Related papers  (2025-04-05T17:25:26Z)
• Quantum autoencoders for image classification [0.0]
  Quantum autoencoders (QAEs) leverage classical optimization solely for parameter tuning.<n>This study introduces a novel image-classification approach using QAEs, achieving classification without requiring additional qubits.
  arXiv  Detail & Related papers  (2025-02-21T07:13:38Z)
• Quantum Mixed-State Self-Attention Network [3.1280831148667105]
  This paper introduces a novel Quantum Mixed-State Self-Attention Network (QMSAN) for natural language processing tasks.<n>QMSAN uses a quantum attention mechanism based on mixed state, allowing for direct similarity estimation between queries and keys in the quantum domain.<n>We also propose an innovative quantum positional encoding scheme, implemented through fixed quantum gates within the circuit, improving the model's ability to capture sequence information without additional qubit resources.
  arXiv  Detail & Related papers  (2024-03-05T11:29:05Z)
• QuanGCN: Noise-Adaptive Training for Robust Quantum Graph Convolutional Networks [124.7972093110732]
  We propose quantum graph convolutional networks (QuanGCN), which learns the local message passing among nodes with the sequence of crossing-gate quantum operations. To mitigate the inherent noises from modern quantum devices, we apply sparse constraint to sparsify the nodes' connections. Our QuanGCN is functionally comparable or even superior than the classical algorithms on several benchmark graph datasets.
  arXiv  Detail & Related papers  (2022-11-09T21:43:16Z)
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage [43.3054117987806]
  We introduce a scalable procedure for harnessing classical computing resources to provide pre-optimized initializations for quantum circuits. We show this method significantly improves the trainability and performance of PQCs on a variety of problems. By demonstrating a means of boosting limited quantum resources using classical computers, our approach illustrates the promise of this synergy between quantum and quantum-inspired models in quantum computing.
  arXiv  Detail & Related papers  (2022-08-29T15:24:03Z)
• QSAN: A Near-term Achievable Quantum Self-Attention Network [73.15524926159702]
  Self-Attention Mechanism (SAM) is good at capturing the internal connections of features. A novel Quantum Self-Attention Network (QSAN) is proposed for image classification tasks on near-term quantum devices.
  arXiv  Detail & Related papers  (2022-07-14T12:22:51Z)
• Quantum circuit architecture search for variational quantum algorithms [88.71725630554758]
  We propose a resource and runtime efficient scheme termed quantum architecture search (QAS) QAS automatically seeks a near-optimal ansatz to balance benefits and side-effects brought by adding more noisy quantum gates. We implement QAS on both the numerical simulator and real quantum hardware, via the IBM cloud, to accomplish data classification and quantum chemistry tasks.
  arXiv  Detail & Related papers  (2020-10-20T12:06:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.