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:2603.21749

Model selection in hybrid quantum neural networks with applications to quantum transformer architectures

Harsh Wadhwa, Rahul Bhowmick, Naipunnya Raj, Rajiv Sangle, Ruchira V. Bhat, Krishnakumar Sabapathy

quant-phcs.LGSubmitted Mar 23, 2026• Announced Mar 24, 2026• 0 citations
arXivHTMLPDF

Abstract

Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective configuration. To address this challenge, we develope the Quantum Bias-Expressivity Toolbox ($\texttt{QBET}$), a framework for evaluating quantum, classical, and hybrid transformer architectures. In this toolbox, we introduce lean metrics for Simplicity Bias ($\texttt{SB}$) and Expressivity ($\texttt{EXP}$), for comparing across various models, and extend the analysis of $\texttt{SB}$ to generative and multiclass-classification tasks. We show that $\texttt{QBET}$ enables efficient pre-screening of promising model variants obviating the need to execute complete training pipelines. In evaluations on transformer-based classification and generative tasks we employ a total of $18$ qubits for embeddings ($6$ qubits each for query, key, and value). We identify scenarios in which quantum self-attention variants surpass their classical counterparts by ranking the respective models according to the $\texttt{SB}$ metric and comparing their relative performance.

Comments
32 Pages. 16 figures, 1 algorithm and 8 tables

Related papers

The Role of Quantum in Hybrid Quantum-Classical Neural Networks: An Empirical Assessment

Dominik Freinberger, Philipp Moser

Quantum machine learning has emerged as a promising application domain for near-term quantum hardware, particularly through hybrid quantum-classical models that leverage both classical and quantum processing. Although numerous hybrid architectures have been proposed and demonstrated successfully on benchmark tasks, a significant open question remains regarding the specific contribution of quantum components to the overall performance of these models. In this work, we aim to shed light on the impact of quantum processing within hybrid quantum-classical neural network architectures through a rigorous statistical study under ideal, noise-free simulation. We systematically assess a selection of commonly used HQNN architectures on three binary medical classification tasks covering medical signal data as well as planar and volumetric images. In doing so, we examine the influence attributable to classical and quantum aspects such as encoding schemes, entanglement, and circuit size. Within this experimental setting, we find that in best-case scenarios, hybrid models show performance comparable to their classical counterparts. However, in most cases, performance metrics deteriorate when the investigated QNN components replace matched classical processing layers. Our multi-modal analysis provides empirical insights into the contributions of the tested quantum components and advocates for cautious claims and design choices for hybrid models in near-term applications.

quant-pharXiv:2601.04732•Jan 9, 2026•1 citation

Hybrid Quantum–Classical Graph Transformers for Efficient Sentiment Analysis

Shamminuj Aktar, Andreas Bärtschi, Abdel‐Hameed A. Badawy +1 more

ABSTRACT Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT) , a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self‐attention. The QGT models variable‐length sentences as token graphs, where both the embedding encoding and the self‐attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and ‐nearest‐neighbor graph structures and evaluate it on five benchmark sentiment‐classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving fewer parameters while requiring 3– fewer samples to reach comparable performance. These findings highlight the potential of graph‐based quantum models as scalable and data‐efficient architectures for natural language understanding.

Advanced Quantum Technologies•Mar 1, 2026•0 citations

Rethinking Expressibility-Trainability Trade-off in Hybrid Quantum Neural Networks

Muhammad Kashif, Muhammad Shafique

Hybrid quantum neural networks (HQNNs) integrate parameterized quantum circuits (PQCs) within classical networks, where the behavior of the underlying PQCs is often the primary focus of analysis. In this context, expressibility and trainability are widely used to characterize PQC's performance and are commonly assumed to exhibit a trade-off, where highly expressive circuits are more susceptible to barren plateaus. However, the validity of this relationship in HQNNs remains unclear. In this paper, we systematically analyze the expressibility--trainability relationship in HQNNs across varying circuit depths, qubit counts, entanglement topologies. We consider different training configurations, including pure PQCs, quantum-only training in hybrid setting, and full end-to-end training of hybrid models. Our results show that pure PQCs exhibit only a weak and regime-dependent trade-off, while hybrid architectures increasingly disrupt and can eliminate this relationship under full hybrid training. This indicates that classical components reshape the optimization landscape, decoupling trainability from PQC expressibility. We further propose a multi-objective neural architecture search (NAS) framework that jointly optimizes expressibility, trainability, and task performance over a combined classical--quantum design space, revealing different Pareto-optimal solutions under full end-to-end and quantum only training in hybrid setting. different trainability definitions. Our results suggest that hybridization is not just an implementation detail, but a defining factor in the performance of quantum machine learning models.

quant-pharXiv:2605.25768•May 26, 2026•0 citations

Learning to maximize quantum neural network expressivity via effective rank

Juan Yao

Abstract Quantum neural networks (QNNs) are widely used as trainable models for solving variational problems, where their ability to represent complex functions directly determines performance. However, accurately quantifying this expressivity remains a major challenge, limiting the understanding of the expressive power of QNNs. Here, we introduce the effective rank κ as a quantitative measure of expressivity. We show that the expressivity of a QNN is determined by the interplay of three factors: the dataset, the measurement operators, and the circuit structure. Unlike conventional metrics based on parameter sampling or entanglement structure, κ captures the number of independent parameters that effectively contribute to the model output, providing an operational and data-dependent characterization of expressivity while avoiding costly parameter sampling. We demonstrate that κ can reach its theoretical maximum 4 n − 1 for an n -qubit system when the circuit architecture, input distribution, and measurement protocol are jointly optimized. Leveraging this insight, we employ κ as a design objective within a reinforcement learning framework with a self-attention transformer agent to automatically discover highly expressive circuit architectures. Our results show that the proposed approach efficiently identifies high-performing circuit configurations, outperforming heuristic designs and random search in terms of sample efficiency. By bridging theoretical characterization with automated design, our approach provides a practical, scalable, and computationally efficient route for constructing expressive quantum circuits, advancing the development of quantum machine learning models.

arXiv:2506.15375•Quantum Science and Technology•May 21, 2026•0 citations

Quantum Neural Networks: A Comparative Analysis and Noise Robustness Evaluation

Tasnim Ahmed, Muhammad Kashif, Alberto Marchisio +1 more

In current noisy intermediate-scale quantum (NISQ) devices, hybrid quantum neural networks (HQNNs) offer a promising solution, combining the strengths of classical machine learning with quantum computing capabilities. However, the performance of these networks can be significantly affected by the quantum noise inherent in NISQ devices. In this paper, we conduct an extensive comparative analysis of various HQNN algorithms, namely Quantum Convolution Neural Network (QCNN), Quanvolutional Neural Network (QuanNN), and Quantum Transfer Learning (QTL), for image classification tasks. We evaluate the performance of each algorithm across quantum circuits with different entangling structures, variations in layer count, and optimal placement in the architecture. Subsequently, we select the highest-performing architectures and assess their robustness against noise influence by introducing quantum gate noise through Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and the Depolarizing Channel. Our results reveal that the top-performing models exhibit varying resilience to different noise gates. However, in most scenarios, the QuanNN demonstrates greater robustness across various quantum noise channels, consistently outperforming other models. This highlights the importance of tailoring model selection to specific noise environments in NISQ devices.

arXiv:2501.14412•Jan 24, 2025•3 citations

A comparative analysis and noise robustness evaluation in quantum neural networks

Tasnim Ahmed, Muhammad Kashif, Alberto Marchisio +1 more

In current noisy intermediate-scale quantum (NISQ) devices, hybrid quantum neural networks (HQNNs) offer a promising solution, combining the strengths of classical machine learning with quantum computing capabilities. However, the performance of these networks can be significantly affected by the quantum noise inherent in NISQ devices. In this paper, we conduct an extensive comparative analysis of various HQNN algorithms, namely Quantum Convolution Neural Network (QCNN), Quanvolutional Neural Network (QuanNN), and Quantum Transfer Learning (QTL), for image classification tasks. We evaluate the performance of each algorithm across quantum circuits with different entangling structures, variations in layer count, and optimal placement in the architecture. Subsequently, we select the highest-performing architectures and assess their robustness against noise influence by introducing quantum gate noise through Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and the Depolarization Channel. Our results reveal that the top-performing models exhibit varying resilience to different noise channels. However, in most scenarios, the QuanNN demonstrates greater robustness across various quantum noise channels, consistently outperforming other models. This highlights the importance of tailoring model selection to specific noise environments in NISQ devices.

Scientific Reports•Sep 29, 2025•22 citations
Quantum machine learning models generally lack principled design guidelines, often requiring full resource-intensive training across numerous choices of encodings, quantum circuit designs and initialization strategies to find effective configuration. To address this challenge, we develope the Quantum Bias-Expressivity Toolbox (QBET\texttt{QBET}QBET), a framework for evaluating quantum, classical, and hybrid transformer architectures. In this toolbox, we introduce lean metrics for Simplicity Bias (SB\texttt{SB}SB) and Expressivity (EXP\texttt{EXP}EXP), for comparing across various models, and extend the analysis of SB\texttt{SB}SB to generative and multiclass-classification tasks. We show that QBET\texttt{QBET}QBET enables efficient pre-screening of promising model variants obviating the need to execute complete training pipelines. In evaluations on transformer-based classification and generative tasks we employ a total of 181818 qubits for embeddings (666 qubits each for query, key, and value). We identify scenarios in which quantum self-attention variants surpass their classical counterparts by ranking the respective models according to the SB\texttt{SB}SB metric and comparing their relative performance.
Quantum machine learning has emerged as a promising application domain for near-term quantum hardware, particularly through hybrid quantum-classical models that leverage both classical and quantum processing. Although numerous hybrid architectures have been proposed and demonstrated successfully on benchmark tasks, a significant open question remains regarding the specific contribution of quantum components to the overall performance of these models. In this work, we aim to shed light on the impact of quantum processing within hybrid quantum-classical neural network architectures through a rigorous statistical study under ideal, noise-free simulation. We systematically assess a selection of commonly used HQNN architectures on three binary medical classification tasks covering medical signal data as well as planar and volumetric images. In doing so, we examine the influence attributable to classical and quantum aspects such as encoding schemes, entanglement, and circuit size. Within this experimental setting, we find that in best-case scenarios, hybrid models show performance comparable to their classical counterparts. However, in most cases, performance metrics deteriorate when the investigated QNN components replace matched classical processing layers. Our multi-modal analysis provides empirical insights into the contributions of the tested quantum components and advocates for cautious claims and design choices for hybrid models in near-term applications.
ABSTRACT Quantum Machine Learning (QML) offers a promising paradigm that leverages quantum computing principles to develop efficient and expressive models for learning from complex and structured data. Recent advances in natural language processing (NLP) and artificial intelligence (AI) have demonstrated capabilities in understanding, generating, and reasoning over linguistic and multimodal information. In this work, we present the Quantum Graph Transformer (QGT) , a hybrid quantum–classical architecture that extends graph transformer capabilities through quantum self‐attention. The QGT models variable‐length sentences as token graphs, where both the embedding encoding and the self‐attention mechanisms are implemented using parameterized quantum circuits (PQCs), enabling efficient contextual learning with significantly fewer trainable parameters. We train QGT using both fully connected and ‐nearest‐neighbor graph structures and evaluate it on five benchmark sentiment‐classification datasets. Experimental results show that QGT consistently achieves higher or comparable accuracy to existing quantum NLP models and outperforms a Classical Graph Transformer (CGT) baseline with identical architecture, achieving fewer parameters while requiring 3– fewer samples to reach comparable performance. These findings highlight the potential of graph‐based quantum models as scalable and data‐efficient architectures for natural language understanding.
Hybrid quantum neural networks (HQNNs) integrate parameterized quantum circuits (PQCs) within classical networks, where the behavior of the underlying PQCs is often the primary focus of analysis. In this context, expressibility and trainability are widely used to characterize PQC's performance and are commonly assumed to exhibit a trade-off, where highly expressive circuits are more susceptible to barren plateaus. However, the validity of this relationship in HQNNs remains unclear. In this paper, we systematically analyze the expressibility--trainability relationship in HQNNs across varying circuit depths, qubit counts, entanglement topologies. We consider different training configurations, including pure PQCs, quantum-only training in hybrid setting, and full end-to-end training of hybrid models. Our results show that pure PQCs exhibit only a weak and regime-dependent trade-off, while hybrid architectures increasingly disrupt and can eliminate this relationship under full hybrid training. This indicates that classical components reshape the optimization landscape, decoupling trainability from PQC expressibility. We further propose a multi-objective neural architecture search (NAS) framework that jointly optimizes expressibility, trainability, and task performance over a combined classical--quantum design space, revealing different Pareto-optimal solutions under full end-to-end and quantum only training in hybrid setting. different trainability definitions. Our results suggest that hybridization is not just an implementation detail, but a defining factor in the performance of quantum machine learning models.
Abstract Quantum neural networks (QNNs) are widely used as trainable models for solving variational problems, where their ability to represent complex functions directly determines performance. However, accurately quantifying this expressivity remains a major challenge, limiting the understanding of the expressive power of QNNs. Here, we introduce the effective rank κ as a quantitative measure of expressivity. We show that the expressivity of a QNN is determined by the interplay of three factors: the dataset, the measurement operators, and the circuit structure. Unlike conventional metrics based on parameter sampling or entanglement structure, κ captures the number of independent parameters that effectively contribute to the model output, providing an operational and data-dependent characterization of expressivity while avoiding costly parameter sampling. We demonstrate that κ can reach its theoretical maximum 4 n − 1 for an n -qubit system when the circuit architecture, input distribution, and measurement protocol are jointly optimized. Leveraging this insight, we employ κ as a design objective within a reinforcement learning framework with a self-attention transformer agent to automatically discover highly expressive circuit architectures. Our results show that the proposed approach efficiently identifies high-performing circuit configurations, outperforming heuristic designs and random search in terms of sample efficiency. By bridging theoretical characterization with automated design, our approach provides a practical, scalable, and computationally efficient route for constructing expressive quantum circuits, advancing the development of quantum machine learning models.
In current noisy intermediate-scale quantum (NISQ) devices, hybrid quantum neural networks (HQNNs) offer a promising solution, combining the strengths of classical machine learning with quantum computing capabilities. However, the performance of these networks can be significantly affected by the quantum noise inherent in NISQ devices. In this paper, we conduct an extensive comparative analysis of various HQNN algorithms, namely Quantum Convolution Neural Network (QCNN), Quanvolutional Neural Network (QuanNN), and Quantum Transfer Learning (QTL), for image classification tasks. We evaluate the performance of each algorithm across quantum circuits with different entangling structures, variations in layer count, and optimal placement in the architecture. Subsequently, we select the highest-performing architectures and assess their robustness against noise influence by introducing quantum gate noise through Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and the Depolarizing Channel. Our results reveal that the top-performing models exhibit varying resilience to different noise gates. However, in most scenarios, the QuanNN demonstrates greater robustness across various quantum noise channels, consistently outperforming other models. This highlights the importance of tailoring model selection to specific noise environments in NISQ devices.
In current noisy intermediate-scale quantum (NISQ) devices, hybrid quantum neural networks (HQNNs) offer a promising solution, combining the strengths of classical machine learning with quantum computing capabilities. However, the performance of these networks can be significantly affected by the quantum noise inherent in NISQ devices. In this paper, we conduct an extensive comparative analysis of various HQNN algorithms, namely Quantum Convolution Neural Network (QCNN), Quanvolutional Neural Network (QuanNN), and Quantum Transfer Learning (QTL), for image classification tasks. We evaluate the performance of each algorithm across quantum circuits with different entangling structures, variations in layer count, and optimal placement in the architecture. Subsequently, we select the highest-performing architectures and assess their robustness against noise influence by introducing quantum gate noise through Phase Flip, Bit Flip, Phase Damping, Amplitude Damping, and the Depolarization Channel. Our results reveal that the top-performing models exhibit varying resilience to different noise channels. However, in most scenarios, the QuanNN demonstrates greater robustness across various quantum noise channels, consistently outperforming other models. This highlights the importance of tailoring model selection to specific noise environments in NISQ devices.