Abstract As quantum computing continues to advance alongside machine learning, Quantum Generative Adversarial Networks (QGANs) have gained attention as a compelling generative modeling approach in quantum machine learning. Despite their potential, most existing QGAN implementations rely on manually designed quantum circuits, which often suffer from high complexity and limited scalability. To overcome these limitations, we propose a Quantum Architecture Search (QAS) method built upon the SuperCircuit framework. This approach enables the automatic discovery of efficient quantum circuit structures tailored for generative tasks, thereby reducing gate count. However, applying SuperCircuit-based QAS directly to QGANs presents two primary challenges: an expansive search space and a lack of guarantees regarding circuit efficiency. To mitigate these issues, we incorporate Principal Component Analysis (PCA) and a PCA-guided feature distribution mechanism during preprocessing. This strategy both compresses the search space and ensures balanced allocation of principal components across sub-generators. Extensive experiments confirm the viability of the proposed framework. When employing the discovered quantum circuits, QAS-QGAN achieves image quality comparable to a state-of-the-art (SOTA) baseline (Silver et al 2023 2023 IEEE/CVF Int. Conf. on Computer Vision (ICCV) pp 7007–16) on both the MNIST and Fashion MNIST datasets. Notably, our model reduces the number of two-qubit gates by 52.08% on MNIST and 52.92% on Fashion MNIST, highlighting substantial improvements in quantum resource efficiency. Furthermore, the model successfully generates high-resolution facial images ( 109 × 89 ) on the CelebA dataset, demonstrating strong scalability and practical applicability.
Abstract As quantum computing continues to advance alongside machine learning, Quantum Generative Adversarial Networks (QGANs) have gained attention as a compelling generative modeling approach in quantum machine learning. Despite their potential, most existing QGAN implementations rely on manually designed quantum circuits, which often suffer from high complexity and limited scalability. To overcome these limitations, we propose a Quantum Architecture Search (QAS) method built upon the SuperCircuit framework. This approach enables the automatic discovery of efficient quantum circuit structures tailored for generative tasks, thereby reducing gate count. However, applying SuperCircuit-based QAS directly to QGANs presents two primary challenges: an expansive search space and a lack of guarantees regarding circuit efficiency. To mitigate these issues, we incorporate Principal Component Analysis (PCA) and a PCA-guided feature distribution mechanism during preprocessing. This strategy both compresses the search space and ensures balanced allocation of principal components across sub-generators. Extensive experiments confirm the viability of the proposed framework. When employing the discovered quantum circuits, QAS-QGAN achieves image quality comparable to a state-of-the-art (SOTA) baseline (Silver et al 2023 2023 IEEE/CVF Int. Conf. on Computer Vision (ICCV) pp 7007–16) on both the MNIST and Fashion MNIST datasets. Notably, our model reduces the number of two-qubit gates by 52.08% on MNIST and 52.92% on Fashion MNIST, highlighting substantial improvements in quantum resource efficiency. Furthermore, the model successfully generates high-resolution facial images ( 109 × 89 ) on the CelebA dataset, demonstrating strong scalability and practical applicability.
Quantum Generative Adversarial Networks (QGANs), as a rising paradigm in Quantum Machine Learning, have shown promising potential in image generation and processing. However, their output quality remains suboptimal, and existing research is largely limited to small-scale, proof-of-concept studies. In this work, we propose a hybrid quantum-classical GAN architecture, where the generator integrates parameterized quantum circuits (PQCs) and classical neural networks. This integration significantly enhances the visual quality of generated images. Our model leverages the complementary strengths of quantum and classical components and outperforms existing methods (Tsang et al. in IEEE Trans. Quantum Eng. 4:1–19, 2023 ; Gulrajani et al. in Proceedings of the 31st international conference on neural information processing systems. NIPS’17, Red Hook, pp. 5769–5779, 2017 ), particularly in terms of image fidelity. Experiments conducted on the MNIST family of datasets show that our hybrid approach achieves a 20.26% average reduction in Fréchet Inception Distance. Furthermore, it improves the Structural Similarity Index Measure, Cosine Similarity, and Peak Signal-to-Noise Ratio by 26.04%, 2.22%, and 7.62%, respectively. These results highlight the effectiveness of combining quantum computing with machine learning, and underscore the potential of hybrid quantum-classical models in advancing generative tasks.
Abstract Quantum generative adversarial networks (QGANs) have demonstrated strong capabilities in tasks like synthetic data generation and detecting anomalies. Recent developments have increasingly integrated traditional machine learning techniques to boost the performance of QGANs. Motivated by this progress, we propose an innovative QGAN architecture that incorporates a classical learning component and employs a dual-generator design. Our approach improves upon the traditional hybrid quantum–classical GAN structure and introduces a redesigned loss function tailored for the new model. Experiments on multiple datasets indicate that our method surpasses previous techniques in image generation quality, achieving a 1.38% average reduction in Fréchet inception distance scores compared to the current state-of-the-art, and improvements of 6.52%, 0.36%, and 0.38% in structural similarity index, cosine similarity, and peak signal-to-noise ratio metrics, respectively. Additionally, our architecture supports the generation of larger images (up to 78 × 78 ), as verified on the CelebA dataset. Simulations conducted in noisy conditions further confirm the robustness and effectiveness of both the proposed architecture and loss function.
Quantum machine learning (QML) has attracted increasing attention due to its excellent performance on clas-sification and identification tasks. In quantum machine learning methods, quantum generative adversarial networks (QGANs) are an extension of classical generative adversarial networks in the field of quantum computing. However, current quan-tum generation techniques are limited by quantum computing resources, these techniques are only validated on small-scale datasets, and the images generated by QGANs are of lower quality. To improve the image quality generated by QGANs, we introduce a new method to construct latent spaces based on quantum principal component analysis, to ensure high-quality data output of QGANs. In addition, we employ a parameterized quantum circuit instead of a sub module of quantum principal component analysis (Quantum Phase Estimation) to reduce the circuit depths and the number of gates. Experimental results indicate that our new method, which utilizes the new latent space as the input for QGANs, outperforms the original QGAN in terms of performance metrics Frechet Inception Distance and Cosine similarity. Specifically, our method achieves a 20 % lower Frechet Inception Distance score and 9 % higher cosine similarity compared to the original QGAN.
As a promising model in Quantum Machine Learning (QML), Quantum Generative Adversarial Networks (QGANs) are rapidly advancing, offering applications in image processing and generation. However, another emerging paradigm represents an image as a Quantum Implicit Neural Representation (QINR). In this work, we propose a novel architectural technique for building QINR-based QGAN to enhance the quality of images generated by QGANs. Additionally, we integrate classical techniques, such as Gradient Penalty and Wasserstein distance, to train QINR-QGAN. In image generation tasks, we demonstrated that QINR-QGAN can achieve performance comparable to state-of-the-art (SOTA) models while significantly reducing the number of trainable quantum parameters. Specifically, QINR-QGAN reduced the trainable quantum parameters by nearly 10 times compared to PQWGAN (Tsang et al. in IEEE Trans. Quantum Eng. 4:1–19, 2023) and Quantum AnoGAN (Herr et al. Quantum Sci. Technol. 6(4): 045004, 2021), demonstrating its superior efficiency in parameter optimization without sacrificing performance. Furthermore, we conducted experiments on the CelebA dataset to tackle a more complex task and generate larger images ( 78×64 ). The results indicate that our model is capable of successfully completing the face generation task.
Generative Adversarial Networks (GANs) is had proven the great results for image generation which opens the gateway for quantum researcher's. But the implementation on quantum computers is not straightforward as each pixel resembles single qubits and to process the 28x28 image it requires 784 qubits. Based on current resources at the number of qubits increase computational time increases. This study explores QGAN potentials to provide a method for generating images using features of quantum systems to improve the quantity and quality of the generated images. This research use the Fashion MNIST dataset because it this dataset has simple as well as complex structures and it consists of 28x28 gray-scale images with 9 fashion products. By considering those limitation of quantum resources for classical computers. Quantum-GAN framework use Principal Component Analysis (PCA) to reduce the number of features. In addition to that, framework is using shallow-depth quantum circuit and a reduced parameter set. This research also deals with vanishing gradient problem of GANs and to overcome this problem of this framework uses Covariance Matrix Adaptation Evolution Strategy (CMA-ES) for fine-tuning training parameters of quantum circuits.
Abstract Quantum machine learning as a field has emerged rather quickly thanks to developments in quantum computing. Of these developments, the one of primary interest is the Quantum Generative Adversarial Network or QGAN which is an enhancement of the familiar GAN to use quantum computation necessary for producing synthetic images. To sum up, based on different types of experiments, QGANs outperformed classical GANs, especially in cases with images such as MNIST and Fashion MNIST datasets. Nevertheless, their capabilities are not fully comprehensible due to existing constraints in quantum systems technology, especially in the NISQ era. In this regard, the current study undertakes a proposed research direction that focuses on improving the resolution of grayscale images that have been produced from the “optdigits” dataset, which contains handwritten digit images. Our work then contrasts this with prior work in terms of FID scores, loss function values, runtime, and the resolution of the images. Further, we extend the work by carrying out the proposed methodology on the FMNIST dataset and provide results to corroborate the efficacy of the proposed technique, besides enabling comparison on the same platform with prior works.