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 Image Processing, Machine Learning and Pattern Recognition (IPMLPR)

Generator and training technique in quantum generative adversarial networks

Quangong Ma, Chaolong Hao, Yunpeng Liu, Nianwen Si, Jiale Zhang, Geng Chen, Dan Qu

Published Sep 13, 2024• 0 citations
Publisher

Abstract

Parameterized quantum circuits play an essential role in the performance of many variational hybrid quantum-classical (HQC) algorithms. One challenge in implementing such algorithms is to choose an effective circuit that well represents the solution space while maintaining a low circuit depth and number of parameters. In this paper, we delve into the influence of utilizing quantum circuits with different types, depths, and widths in the Quantum Generative Adversarial Network (QGAN) generator on its overall performance. Our findings reveal that employing parametric two-qubit gates in the QGAN generator slightly outperforms the use of fixed-parameter two-qubit gates. Additionally, as the number of quantum circuit layers increases (i.e., the circuit depth), the performance of the QGAN generator improves, though there exists ’saturation’ where further layer addition leads to a decline in performance. Furthermore, considering the number of qubits available for the QGAN generator to accomplish the generation task, we observe a gradual decline in QGAN's performance as the number of ancillary qubits (i.e., circuit width) increases, though it still outperforms the scenario without auxiliary qubits. Additionally, we introduce the Unrolled QGAN model, which incorporates the Unrolled training technique to improve the performance of QGAN. Our experimental results demonstrate that this technique effectively enhances the performance of the QGAN.

DOI
10.1145/3700906.3701003

Related papers

Designing Effective Quantum Generators: A Comparative Study of Variational Ansätze in Hybrid QGANs

Sarvapriya M. Tripathi, Aakarsh Etar, Jayesh Soni +1 more

Quantum Generative Adversarial Networks (QGANs) combine quantum circuit based generative models with classical discriminators to exploit quantum advantages in generative modeling. This work investigates a hybrid QGAN architecture with a quantum-enhanced generator and a classical discriminator, applied to the Modified National Institute of Standards and Technology (MNIST) dataset. We implement and benchmark three different quantum circuit ansätze - namely a basic entangler circuit, a simple two-design circuit and a strongly entangling circuit, with each QGAN model being constructed using six layers of the respective ansätze. To manage the 28x28 image complexity, the generator employs a patch wise scheme, dividing each image into small patches generated by separate sub-circuits. The performance of each ansatz is evaluated in terms of training stability and output image quality. Our results demonstrate that the choice of quantum circuit ansatz significantly impacts the QGAN’s ability to learn the distribution of handwritten digits. In particular, the strongly entangling ansatz achieves the best performance at the cost of stability and image fidelity among the three yielding recognizable digit images. While no quantum advantage was demonstrated, this study provides comparative analysis and insights into designing effective quantum generators for hybrid QGANs on image data, serving as a benchmark for future developments in quantum-enhanced generative models.

IEEE International Conference on AI in Cybersecurity (ICAIC)•Feb 18, 2026•0 citations

Re-QGAN: an optimized adversarial quantum circuit learning framework

Sandra Nguemto, Vicente Leyton‐Ortega

Adversarial learning represents a powerful technique for generating data statistics. Its successful implementation in quantum computational platforms is not straightforward due to limitations in connectivity, quantum operation fidelity, and limited access to the quantum processor for statistically relevant results. Constraining the number of quantum operations and providing a design with a low compilation cost, we propose a quantum generative adversarial network design that uses real Hilbert spaces as the framework for the generative model and a novel strategy to encode classical information into the quantum framework. We consider quantum generator and discriminator architectures based on a variational quantum circuit. We encode classical information by the stereographic projection, which allows us to use the entire classical domain without normalization procedures. For low-depth ansätze designs, we consider the real Hilbert space as the working space for the quantum adversarial game. This architecture improves state-of-the-art quantum generative adversarial performance while maintaining a shallow-depth quantum circuit and a reduced parameter set. We tested our design in a low resource regime, generating handwritten digits with the MNIST as the reference dataset. We could generate undetected data (digits) with just 15 epochs working in the real Hilbert space of 2, 3, and 4 qubits. Our design uses native quantum operations established in superconducting-based quantum processors and is compatible with ion-trapped-based architectures.

arXiv:2208.02165•Aug 3, 2022•6 citations

Optimizing Entangling Power and Preserving Circuit Symmetry in Hybrid Quantum Generative Adversarial Networks for Expressive Variational Generation

Wei Ding, Yan Liang, Zijun Guo +3 more

Abstract This work presents a Hybrid Quantum Generative Adversarial Network (HQGAN) that combines symmetry-preserving variational quantum circuits with entangling power optimization, targeting improved expressivity and training stability on NISQ devices. The quantum generator employs layered parameterized circuits composed of Ising-type entangling gates and symmetric single-qubit rotations, inspired by convolutional neural networks. To guide circuit design, we quantify the entanglement capability of each layer using the entangling power (EP) metric via Monte Carlo sampling. Compared to traditional fully connected architectures, HQGAN introduces three major improvements: (1) symmetry-preserving gates preserve translational invariance and enhance feature extraction; (2) modular subcircuit designs with patch-wise outputs reduce parameter overhead by 50\% while improving convergence; (3) optimized entanglement via EP leads to better initialization and performance. Experimental results on Fashion-MNIST and OptDigits demonstrate that HQGAN achieves the same level of fidelity as the original model within 400 epochs,The KL divergence of the entanglement-enhanced Ising-based model is reduced to 0.023, compared to the baseline model. Moreover,parameter complexity is reduced from \( O(N^2) \) to \( O(\mathrm{poly}(N)) \), alleviating overfitting and improving generalization. These results confirm the importance of structure-aware circuit design and entanglement-driven optimization for quantum generative modeling under near-term constraints.

•Jul 11, 2025•0 citations

Hybrid Quantum-Classical Generative Adversarial Network for Patch-Based Image Generation

Jen-Sheng Tsai, Li-Yin Cai

Quantum generative adversarial networks (QGANs) have attracted increasing attention for their potential to surpass classical generative models by leveraging the expressive power of parameterized quantum circuits (PQCs). However, in the current noisy intermediate-scale quantum era, the implementation of fully quantum algorithms is hindered by hardware limitations, restricting most existing approaches to low-resolution generated image. To address this challenge, we propose a hybrid quantum-classical generative adversarial network for patch-based image generation. Our method employs dual PQC-based generators that decompose images into structured patches, while local and global classical discriminators jointly capture local details and preserve global structural coherence. This design addresses scalability limitations of existing QGANs and mitigates patch-boundary artifacts, thereby enabling high-resolution image generation on hardware with restricted qubit counts. Experimental results validate the effectiveness of the proposed method, demonstrating improvements in image fidelity over existing baselines, and providing insights into the influence of qubit count on generative performance.

International Conference on Information and Communication Technology Convergence (ICTC)•Oct 14, 2025•0 citations

Experimental demonstration of a quantum generative adversarial network for continuous distributions

Abhinav Anand, Jonathan Romero, Matthias Degroote +1 more

The potential advantage of machine learning in quantum computers is a topic of intense discussion in the literature. Theoretical, numerical and experimental explorations will most likely be required to understand its power. There has been different algorithms proposed to exploit the probabilistic nature of variational quantum circuits for generative modelling. In this paper, we employ a hybrid architecture for quantum generative adversarial networks (QGANs) and study their robustness in the presence of noise. We devise a simple way of adding different types of noise to the quantum generator circuit, and numerically simulate the noisy hybrid QGANs to learn continuous probability distributions, and show that the performance of HQGANs remain unaffected. We also investigate the effect of different parameters on the training time to reduce the computational scaling of the algorithm and simplify its deployment on a quantum computer. We then perform the training on Rigetti's Aspen-4-2Q-A quantum processing unit, and present the results from the training. Our results pave the way for experimental exploration of different quantum machine learning algorithms on noisy intermediate scale quantum devices.

•Jun 2, 2020•10 citations

Quantum Generative Adversarial Networks (QGANs) for Data Augmentation

Jincheng Zhang

This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) to data augmentation for machine learning. Traditional Generative Adversarial Networks (GANs) rely on classical neural networks, while this research explores leveraging quantum circuits as generators within a QGAN architecture. The core idea is to train a quantum generator to produce synthetic data samples, supplementing existing datasets with novel instances. The discriminator remains a classical neural network, tasked with distinguishing between real and generated data. We present a theoretical framework for this approach, outlining the mathematical formulation and key components. Specifically, we introduce the notation (x, s_1, s_2, ..., s_K) to represent data samples, generator states, and relevant parameters. The objective function for the QGAN is defined as minimizing the Jensen-Shannon divergence between the real and generated data distributions. The effectiveness of this approach is discussed, highlighting potential advantages and challenges. This work contributes to the emerging field of quantum machine learning and offers a novel strategy for improving the performance of machine learning models, particularly in scenarios with limited training data.

•Aug 31, 2026•0 citations
Parameterized quantum circuits play an essential role in the performance of many variational hybrid quantum-classical (HQC) algorithms. One challenge in implementing such algorithms is to choose an effective circuit that well represents the solution space while maintaining a low circuit depth and number of parameters. In this paper, we delve into the influence of utilizing quantum circuits with different types, depths, and widths in the Quantum Generative Adversarial Network (QGAN) generator on its overall performance. Our findings reveal that employing parametric two-qubit gates in the QGAN generator slightly outperforms the use of fixed-parameter two-qubit gates. Additionally, as the number of quantum circuit layers increases (i.e., the circuit depth), the performance of the QGAN generator improves, though there exists ’saturation’ where further layer addition leads to a decline in performance. Furthermore, considering the number of qubits available for the QGAN generator to accomplish the generation task, we observe a gradual decline in QGAN's performance as the number of ancillary qubits (i.e., circuit width) increases, though it still outperforms the scenario without auxiliary qubits. Additionally, we introduce the Unrolled QGAN model, which incorporates the Unrolled training technique to improve the performance of QGAN. Our experimental results demonstrate that this technique effectively enhances the performance of the QGAN.
Quantum Generative Adversarial Networks (QGANs) combine quantum circuit based generative models with classical discriminators to exploit quantum advantages in generative modeling. This work investigates a hybrid QGAN architecture with a quantum-enhanced generator and a classical discriminator, applied to the Modified National Institute of Standards and Technology (MNIST) dataset. We implement and benchmark three different quantum circuit ansätze - namely a basic entangler circuit, a simple two-design circuit and a strongly entangling circuit, with each QGAN model being constructed using six layers of the respective ansätze. To manage the 28x28 image complexity, the generator employs a patch wise scheme, dividing each image into small patches generated by separate sub-circuits. The performance of each ansatz is evaluated in terms of training stability and output image quality. Our results demonstrate that the choice of quantum circuit ansatz significantly impacts the QGAN’s ability to learn the distribution of handwritten digits. In particular, the strongly entangling ansatz achieves the best performance at the cost of stability and image fidelity among the three yielding recognizable digit images. While no quantum advantage was demonstrated, this study provides comparative analysis and insights into designing effective quantum generators for hybrid QGANs on image data, serving as a benchmark for future developments in quantum-enhanced generative models.
Adversarial learning represents a powerful technique for generating data statistics. Its successful implementation in quantum computational platforms is not straightforward due to limitations in connectivity, quantum operation fidelity, and limited access to the quantum processor for statistically relevant results. Constraining the number of quantum operations and providing a design with a low compilation cost, we propose a quantum generative adversarial network design that uses real Hilbert spaces as the framework for the generative model and a novel strategy to encode classical information into the quantum framework. We consider quantum generator and discriminator architectures based on a variational quantum circuit. We encode classical information by the stereographic projection, which allows us to use the entire classical domain without normalization procedures. For low-depth ansätze designs, we consider the real Hilbert space as the working space for the quantum adversarial game. This architecture improves state-of-the-art quantum generative adversarial performance while maintaining a shallow-depth quantum circuit and a reduced parameter set. We tested our design in a low resource regime, generating handwritten digits with the MNIST as the reference dataset. We could generate undetected data (digits) with just 15 epochs working in the real Hilbert space of 2, 3, and 4 qubits. Our design uses native quantum operations established in superconducting-based quantum processors and is compatible with ion-trapped-based architectures.
Abstract This work presents a Hybrid Quantum Generative Adversarial Network (HQGAN) that combines symmetry-preserving variational quantum circuits with entangling power optimization, targeting improved expressivity and training stability on NISQ devices. The quantum generator employs layered parameterized circuits composed of Ising-type entangling gates and symmetric single-qubit rotations, inspired by convolutional neural networks. To guide circuit design, we quantify the entanglement capability of each layer using the entangling power (EP) metric via Monte Carlo sampling. Compared to traditional fully connected architectures, HQGAN introduces three major improvements: (1) symmetry-preserving gates preserve translational invariance and enhance feature extraction; (2) modular subcircuit designs with patch-wise outputs reduce parameter overhead by 50\% while improving convergence; (3) optimized entanglement via EP leads to better initialization and performance. Experimental results on Fashion-MNIST and OptDigits demonstrate that HQGAN achieves the same level of fidelity as the original model within 400 epochs,The KL divergence of the entanglement-enhanced Ising-based model is reduced to 0.023, compared to the baseline model. Moreover,parameter complexity is reduced from O(N2) O(N^2) O(N2) to O(poly(N)) O(\mathrm{poly}(N)) O(poly(N)), alleviating overfitting and improving generalization. These results confirm the importance of structure-aware circuit design and entanglement-driven optimization for quantum generative modeling under near-term constraints.
Quantum generative adversarial networks (QGANs) have attracted increasing attention for their potential to surpass classical generative models by leveraging the expressive power of parameterized quantum circuits (PQCs). However, in the current noisy intermediate-scale quantum era, the implementation of fully quantum algorithms is hindered by hardware limitations, restricting most existing approaches to low-resolution generated image. To address this challenge, we propose a hybrid quantum-classical generative adversarial network for patch-based image generation. Our method employs dual PQC-based generators that decompose images into structured patches, while local and global classical discriminators jointly capture local details and preserve global structural coherence. This design addresses scalability limitations of existing QGANs and mitigates patch-boundary artifacts, thereby enabling high-resolution image generation on hardware with restricted qubit counts. Experimental results validate the effectiveness of the proposed method, demonstrating improvements in image fidelity over existing baselines, and providing insights into the influence of qubit count on generative performance.
The potential advantage of machine learning in quantum computers is a topic of intense discussion in the literature. Theoretical, numerical and experimental explorations will most likely be required to understand its power. There has been different algorithms proposed to exploit the probabilistic nature of variational quantum circuits for generative modelling. In this paper, we employ a hybrid architecture for quantum generative adversarial networks (QGANs) and study their robustness in the presence of noise. We devise a simple way of adding different types of noise to the quantum generator circuit, and numerically simulate the noisy hybrid QGANs to learn continuous probability distributions, and show that the performance of HQGANs remain unaffected. We also investigate the effect of different parameters on the training time to reduce the computational scaling of the algorithm and simplify its deployment on a quantum computer. We then perform the training on Rigetti's Aspen-4-2Q-A quantum processing unit, and present the results from the training. Our results pave the way for experimental exploration of different quantum machine learning algorithms on noisy intermediate scale quantum devices.
This paper investigates the application of Quantum Generative Adversarial Networks (QGANs) to data augmentation for machine learning. Traditional Generative Adversarial Networks (GANs) rely on classical neural networks, while this research explores leveraging quantum circuits as generators within a QGAN architecture. The core idea is to train a quantum generator to produce synthetic data samples, supplementing existing datasets with novel instances. The discriminator remains a classical neural network, tasked with distinguishing between real and generated data. We present a theoretical framework for this approach, outlining the mathematical formulation and key components. Specifically, we introduce the notation (x, s_1, s_2, ..., s_K) to represent data samples, generator states, and relevant parameters. The objective function for the QGAN is defined as minimizing the Jensen-Shannon divergence between the real and generated data distributions. The effectiveness of this approach is discussed, highlighting potential advantages and challenges. This work contributes to the emerging field of quantum machine learning and offers a novel strategy for improving the performance of machine learning models, particularly in scenarios with limited training data.