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

International Conference on Quantum Communications, Networking, and Computing (QCNC)

TNO-QA: Tensor-Network Optimized Quantum Attention

Yaswitha Gujju, Romain Harang, Tetsuo Shibuya

Published Apr 6, 2026• 0 citations
Publisher

Abstract

We propose Tensor-Network Optimized Quantum Attention (TNO-QA), a hybrid quantum-classical framework that reduces the parameter overhead of classical attention mechanisms. TNO-QA combines low-rank tensor parameterization with a Quantum Train module to form a compact yet expressive attention block. In this design, Tensor-Train (TT) cores generate parameters for a fixed Parameterized Quantum Circuit (PQC) within the quantum train, whose outputs are processed by the associated Multi-Layer Perceptron (MLP) to produce the attention weights. This approach enables fully differentiable optimization in the classical domain, while the quantum circuit operates only in the forward pass, mitigating barren plateaus and quantum noise. A batched parameter generation scheme further reduces qubit requirements logarithmically, enhancing scalability. We integrate TNO-QA into U-Net architectures for diffusion models and evaluate on CIFAR-10, MNIST, and FMNIST. Experiments demonstrate$57-65 \%$reduction in attention parameters while maintaining comparable reconstruction quality and improving Fréchet Inception Distance relative to classical attention. TNO-QA is architecture-agnostic and supports multi-scale attention hierarchies, providing a scalable, stable, and hardware-efficient pathway toward practical quantum-assisted deep learning.

DOI
10.1109/qcnc69040.2026.00124

Related papers

Quantum-Train with Tensor Network Mapping Model and Distributed Circuit Ansatz

Chen-Yu Liu, Chu-Hsuan Abraham Lin, Kuan‐Cheng Chen

In the Quantum-Train (QT) framework, mapping quantum state measurements to classical neural network weights is a critical challenge that affects the scalability and efficiency of hybrid quantum-classical models. The traditional QT framework employs a multi-layer perceptron (MLP) for this task, but it struggles with scalability and interpretability. To address these issues, we propose replacing the MLP with a tensor network-based model and introducing a distributed circuit ansatz designed for large-scale quantum machine learning with multiple small quantum processing unit nodes. This approach enhances scalability, efficiently represents high-dimensional data, and maintains a compact model structure. Our enhanced QT framework retains the benefits of reduced parameter count and independence from quantum resources during inference. Experimental results on benchmark datasets demonstrate that the tensor network-based QT framework achieves competitive performance with improved efficiency and generalization, offering a practical solution for scalable hybrid quantum-classical machine learning.

arXiv:2409.06992•IEEE International Conference on Acoustics Speech and Signal Processing•Mar 12, 2025•15 citations

Quantum Adaptive Excitation Network with Variational Quantum Circuits for Channel Attention

Yu-Chao Hsu, Kuan‐Cheng Chen, Tai-Yue Li +1 more

In this work, we introduce the Quantum Adaptive Excitation Network (QAE-Net), a hybrid quantum-classical framework designed to enhance channel attention mechanisms in Convolutional Neural Networks (CNNs). QAE-Net replaces the classical excitation block of Squeeze-and-Excitation modules with a shallow Variational Quantum Circuit (VQC), leveraging quantum superposition and entanglement to capture higher-order inter-channel dependencies that are challenging to model with purely classical approaches. We evaluate QAE-Net on benchmark image classification tasks, including MNIST, FashionMNIST, and CIFAR-10, and observe consistent performance improvements across all datasets, with particularly notable gains on tasks involving three-channel inputs. Furthermore, experimental results demonstrate that increasing the number of variational layers in the quantum circuit leads to progressively higher classification accuracy, underscoring the expressivity benefits of deeper quantum models. These findings highlight the potential of integrating VQCs into CNN architectures to improve representational capacity while maintaining compatibility with nearterm quantum devices. The proposed approach is tailored for the Noisy Intermediate-Scale Quantum (NISQ) era, offering a scalable and feasible pathway for deploying quantum-enhanced attention mechanisms in practical deep learning workflows.

arXiv:2507.11217•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•7 citations

Tensor ring optimized quantum-enhanced tensor neural networks

Debanjan Konar, Dheeraj Peddireddy, Bijaya Ketan Panigrahi +1 more

Abstract Quantum machine learning researchers often rely on incorporating tensor networks (TN) into deep neural networks (DNN) and variational optimization. However, the standard optimization techniques used for training the contracted trainable weights of each model layer suffer from the correlations and entanglement structure between the model parameters in classical implementations. To address this issue, a multi-layer design of a tensor ring optimized variational quantum learning classifier (Quan-TR) comprising cascading entangling gates replacing the fully connected (dense) layers of a TN is proposed, and it is referred to as tensor ring optimized quantum-enhanced tensor neural networks (TR-QNet). TR-QNet parameters are optimized using the stochastic gradient descent algorithm on qubit measurements. The proposed TR-QNet is evaluated on three distinct datasets, namely Iris, MNIST, and CIFAR-10, to demonstrate the enhanced precision achieved for binary classification. In quantum simulations, the proposed TR-QNet achieves promising precision of $$94.5\%$$ 94.5 % , $$86.16\%$$ 86.16 % , and $$83.54\%$$ 83.54 % on the Iris, MNIST, and CIFAR-10 datasets. Benchmark studies have been conducted on state-of-the-art quantum and classical implementations of TN models to show the efficacy of the proposed TR-QNet. Moreover, the scalability of TR-QNet highlights its potential for exhibiting in deep learning applications on a large scale. The PyTorch implementation of TR-QNet is available on Github https://github.com/konar1987/TR-QNet/ .

arXiv:2310.01515•Quantum Machine Intelligence•Apr 22, 2025•4 citations

Tree Tensor Network Quantum-Classical Hybrid Neural Architecture for Efficient Data Classification

Novianto Nur Hidayat, Muhamad Akrom

We introduce the Tree Tensor Network-enhanced Quantum-Classical Neural Network (TTN-QNet), a hybrid architecture that leverages the hierarchical structure of Tree Tensor Networks for efficient parameter representation and Variational Quantum Circuits (VQC) for expressive modeling. Unlike Tensor Ring Networks, TTNs reduce parameter redundancy through a tree-based topology, enabling scalable and interpretable computation. The proposed TTN-QNet is evaluated on the Iris, MNIST, and CIFAR-10 datasets, achieving classification accuracies of 93.2%, 85.24%, and 81.67%, respectively, on binary classification tasks. TTN-QNet demonstrates rapid convergence and robustness against barren plateaus, offering a promising direction for deep quantum learning.

Journal of Multiscale Materials Informatics•Jun 14, 2025•3 citations

Hybrid Quantum-Classical Training in Quantum Neural Networks: A Framework for Bridging Parameterized Quantum Circuits and Classical Optimization

Matthew Busel

Quantum Neural Networks (QNNs) represent a compelling convergence of quantum mechanics and machine learning, yet their practical deployment remains constrained by noise, limited qubit counts, and the cost of full quantum execution. Hybrid quantum-classical (HQC) training offers a pragmatic path forward: parameterized quantum circuits (PQCs) process information in exponentially large Hilbert spaces while classical optimizers update parameters via gradient methods accessible on today's hardware. We present a modular HQC training framework, formalising the parameter-shift rule for hardware-compatible gradient estimation, characterising the barren-plateau phenomenon through a variance-decay analysis, and introducing noise-aware training strategies for NISQ devices. Empirical results from state-vector and shot-based simulation confirm measurable quantum advantage on quantum-structured tasks, with the phase classification benchmark improving +12.1% over a classical MLP baseline. The accompanying open-source library provides a clean abstraction between quantum simulation and classical optimisation, serving as a foundation for near-term quantum machine learning research.

•Mar 3, 2026•0 citations

Vehicle Routing Problems via Quantum Graph Attention Network Deep Reinforcement Learning

Le Tung Giang, Vu Hoang Viet, Nguyen Xuan Tung +2 more

The vehicle routing problem (VRP) is a fundamental NP-hard task in intelligent transportation systems with broad applications in logistics and distribution. Deep reinforcement learning (DRL) with Graph Neural Networks (GNNs) has shown promise, yet classical models rely on large multi-layer perceptrons (MLPs) that are parameter-heavy and memory-bound. We propose a Quantum Graph Attention Network (Q-GAT) within a DRL framework, where parameterized quantum circuits (PQCs) replace conventional MLPs at critical readout stages. The hybrid model maintains the expressive capacity of graph attention encoders while reducing trainable parameters by more than 50%. Using proximal policy optimization (PPO) with greedy and stochastic decoding, experiments on VRP benchmarks show that Q-GAT achieves faster convergence and reduces routing cost by about 5% compared with classical GAT baselines. These results demonstrate the potential of PQC-enhanced GNNs as compact and effective solvers for large-scale routing and logistics optimization.

cs.LGCross-listedarXiv:2511.15175•Nov 20, 2025•1 citation
We propose Tensor-Network Optimized Quantum Attention (TNO-QA), a hybrid quantum-classical framework that reduces the parameter overhead of classical attention mechanisms. TNO-QA combines low-rank tensor parameterization with a Quantum Train module to form a compact yet expressive attention block. In this design, Tensor-Train (TT) cores generate parameters for a fixed Parameterized Quantum Circuit (PQC) within the quantum train, whose outputs are processed by the associated Multi-Layer Perceptron (MLP) to produce the attention weights. This approach enables fully differentiable optimization in the classical domain, while the quantum circuit operates only in the forward pass, mitigating barren plateaus and quantum noise. A batched parameter generation scheme further reduces qubit requirements logarithmically, enhancing scalability. We integrate TNO-QA into U-Net architectures for diffusion models and evaluate on CIFAR-10, MNIST, and FMNIST. Experiments demonstrate57−65%57-65 \%57−65%reduction in attention parameters while maintaining comparable reconstruction quality and improving Fréchet Inception Distance relative to classical attention. TNO-QA is architecture-agnostic and supports multi-scale attention hierarchies, providing a scalable, stable, and hardware-efficient pathway toward practical quantum-assisted deep learning.
In the Quantum-Train (QT) framework, mapping quantum state measurements to classical neural network weights is a critical challenge that affects the scalability and efficiency of hybrid quantum-classical models. The traditional QT framework employs a multi-layer perceptron (MLP) for this task, but it struggles with scalability and interpretability. To address these issues, we propose replacing the MLP with a tensor network-based model and introducing a distributed circuit ansatz designed for large-scale quantum machine learning with multiple small quantum processing unit nodes. This approach enhances scalability, efficiently represents high-dimensional data, and maintains a compact model structure. Our enhanced QT framework retains the benefits of reduced parameter count and independence from quantum resources during inference. Experimental results on benchmark datasets demonstrate that the tensor network-based QT framework achieves competitive performance with improved efficiency and generalization, offering a practical solution for scalable hybrid quantum-classical machine learning.
In this work, we introduce the Quantum Adaptive Excitation Network (QAE-Net), a hybrid quantum-classical framework designed to enhance channel attention mechanisms in Convolutional Neural Networks (CNNs). QAE-Net replaces the classical excitation block of Squeeze-and-Excitation modules with a shallow Variational Quantum Circuit (VQC), leveraging quantum superposition and entanglement to capture higher-order inter-channel dependencies that are challenging to model with purely classical approaches. We evaluate QAE-Net on benchmark image classification tasks, including MNIST, FashionMNIST, and CIFAR-10, and observe consistent performance improvements across all datasets, with particularly notable gains on tasks involving three-channel inputs. Furthermore, experimental results demonstrate that increasing the number of variational layers in the quantum circuit leads to progressively higher classification accuracy, underscoring the expressivity benefits of deeper quantum models. These findings highlight the potential of integrating VQCs into CNN architectures to improve representational capacity while maintaining compatibility with nearterm quantum devices. The proposed approach is tailored for the Noisy Intermediate-Scale Quantum (NISQ) era, offering a scalable and feasible pathway for deploying quantum-enhanced attention mechanisms in practical deep learning workflows.
Abstract Quantum machine learning researchers often rely on incorporating tensor networks (TN) into deep neural networks (DNN) and variational optimization. However, the standard optimization techniques used for training the contracted trainable weights of each model layer suffer from the correlations and entanglement structure between the model parameters in classical implementations. To address this issue, a multi-layer design of a tensor ring optimized variational quantum learning classifier (Quan-TR) comprising cascading entangling gates replacing the fully connected (dense) layers of a TN is proposed, and it is referred to as tensor ring optimized quantum-enhanced tensor neural networks (TR-QNet). TR-QNet parameters are optimized using the stochastic gradient descent algorithm on qubit measurements. The proposed TR-QNet is evaluated on three distinct datasets, namely Iris, MNIST, and CIFAR-10, to demonstrate the enhanced precision achieved for binary classification. In quantum simulations, the proposed TR-QNet achieves promising precision of 94.5%94.5\%94.5% 94.5 % , 86.16%86.16\%86.16% 86.16 % , and 83.54%83.54\%83.54% 83.54 % on the Iris, MNIST, and CIFAR-10 datasets. Benchmark studies have been conducted on state-of-the-art quantum and classical implementations of TN models to show the efficacy of the proposed TR-QNet. Moreover, the scalability of TR-QNet highlights its potential for exhibiting in deep learning applications on a large scale. The PyTorch implementation of TR-QNet is available on Github https://github.com/konar1987/TR-QNet/ .
We introduce the Tree Tensor Network-enhanced Quantum-Classical Neural Network (TTN-QNet), a hybrid architecture that leverages the hierarchical structure of Tree Tensor Networks for efficient parameter representation and Variational Quantum Circuits (VQC) for expressive modeling. Unlike Tensor Ring Networks, TTNs reduce parameter redundancy through a tree-based topology, enabling scalable and interpretable computation. The proposed TTN-QNet is evaluated on the Iris, MNIST, and CIFAR-10 datasets, achieving classification accuracies of 93.2%, 85.24%, and 81.67%, respectively, on binary classification tasks. TTN-QNet demonstrates rapid convergence and robustness against barren plateaus, offering a promising direction for deep quantum learning.
Quantum Neural Networks (QNNs) represent a compelling convergence of quantum mechanics and machine learning, yet their practical deployment remains constrained by noise, limited qubit counts, and the cost of full quantum execution. Hybrid quantum-classical (HQC) training offers a pragmatic path forward: parameterized quantum circuits (PQCs) process information in exponentially large Hilbert spaces while classical optimizers update parameters via gradient methods accessible on today's hardware. We present a modular HQC training framework, formalising the parameter-shift rule for hardware-compatible gradient estimation, characterising the barren-plateau phenomenon through a variance-decay analysis, and introducing noise-aware training strategies for NISQ devices. Empirical results from state-vector and shot-based simulation confirm measurable quantum advantage on quantum-structured tasks, with the phase classification benchmark improving +12.1% over a classical MLP baseline. The accompanying open-source library provides a clean abstraction between quantum simulation and classical optimisation, serving as a foundation for near-term quantum machine learning research.
The vehicle routing problem (VRP) is a fundamental NP-hard task in intelligent transportation systems with broad applications in logistics and distribution. Deep reinforcement learning (DRL) with Graph Neural Networks (GNNs) has shown promise, yet classical models rely on large multi-layer perceptrons (MLPs) that are parameter-heavy and memory-bound. We propose a Quantum Graph Attention Network (Q-GAT) within a DRL framework, where parameterized quantum circuits (PQCs) replace conventional MLPs at critical readout stages. The hybrid model maintains the expressive capacity of graph attention encoders while reducing trainable parameters by more than 50%. Using proximal policy optimization (PPO) with greedy and stochastic decoding, experiments on VRP benchmarks show that Q-GAT achieves faster convergence and reduces routing cost by about 5% compared with classical GAT baselines. These results demonstrate the potential of PQC-enhanced GNNs as compact and effective solvers for large-scale routing and logistics optimization.