The development of compact and controllable generative models under resource constraints remains a critical challenge for the practical deployment of conditional generative adversarial networks (cGANs). In this work, QuCon-GAN, a hybrid quantum-classical conditional GAN, is proposed to enhance generation expressiveness while drastically reducing parameter counts. Within the generator, dynamic data re-upload, parameterized unitary transformations, and adaptive entanglement have been incorporated into a variational quantum circuit, thereby enabling continuous semantic guidance and feature refinement across layers. When compared to classical counterparts, QuCon-GAN achieves significant improvements in parameter efficiency and conditional control, supporting full-category generation on the MNIST dataset at a resolution of 32×32 pixels. Extensive experiments have demonstrated that QuCon-GAN attains a Fréchet Inception Distance (FID) of 52.42, while maintaining stable adversarial training and avoiding mode collapse even under limited quantum resources (8 qubits). Furthermore, systematic comparisons against classical baselines and recent quantum GANs have validated the effectiveness of QuCon-GAN in balancing resource efficiency, stability, and semantic controllability. This work demonstrates the potential of hybrid quantum-classical architectures for advancing lightweight generative modeling in the Noisy Intermediate-Scale Quantum (NISQ) era.
The development of compact and controllable generative models under resource constraints remains a critical challenge for the practical deployment of conditional generative adversarial networks (cGANs). In this work, QuCon-GAN, a hybrid quantum-classical conditional GAN, is proposed to enhance generation expressiveness while drastically reducing parameter counts. Within the generator, dynamic data re-upload, parameterized unitary transformations, and adaptive entanglement have been incorporated into a variational quantum circuit, thereby enabling continuous semantic guidance and feature refinement across layers. When compared to classical counterparts, QuCon-GAN achieves significant improvements in parameter efficiency and conditional control, supporting full-category generation on the MNIST dataset at a resolution of 32×32 pixels. Extensive experiments have demonstrated that QuCon-GAN attains a Fréchet Inception Distance (FID) of 52.42, while maintaining stable adversarial training and avoiding mode collapse even under limited quantum resources (8 qubits). Furthermore, systematic comparisons against classical baselines and recent quantum GANs have validated the effectiveness of QuCon-GAN in balancing resource efficiency, stability, and semantic controllability. This work demonstrates the potential of hybrid quantum-classical architectures for advancing lightweight generative modeling in the Noisy Intermediate-Scale Quantum (NISQ) era.
Abstract Quantum machine learning (QML) has garnered significant attention for its potential to outperform classical machine learning.A notable area within QML is quantum generative adversarial networks (QGANs), which serve as the quantum equivalent to classical GANs, commonly used in image processing and generation.However, the content of images generated by existing QGANs is still uncontrollable.In this work, we introduce a conditional encoder for the quantum generator, enabling it to controllably produce multiple image types.While this approach can, in principle, be extended to any number of conditional generations, its practical applicability is limited by the finite qubit resources available.Our results show that it can generate images of satisfactory quality, with a Frechet Inception Distance (FID) score of 201.6, a Kernel Inception Distance (KID) score of 0.281, and a Learned Perceptual Image Patch Similarity (LPIPS) score of 0.461.Through quantum noise experiments, we show that when the noise intensity reaches 0.2, the relative changes in FID, KID, and LPIPS remain below 5%, indicating that the model is robust to moderate noise levels.Furthermore, in comparative experiments against without multicondition or limitted multicondition, our method outperforms the strongest baseline by 3%−11% , thereby demonstrating its stable superiority over current approaches.
Hybrid Quantum Generative Adversarial Networks (QGANs) represent one of the most promising convergences between quantum computation and deep learning. This survey consolidates developments in hybrid QGANs from 2021 to 2025 and highlights the emergence of the Quantum Implicit Neural Representation GAN (QINR-QGAN) as a state-of-the-art model. We examine architectural innovations, hybrid-layer mechanisms, quantum feature encodings, and training dynamics. Chronological analysis shows that advances such as data re-uploading circuits, strongly entangling layers, and implicit neural representations have significantly improved generative performance, convergence, and interpretability. Comparative experiments demonstrate up to 18 % improvement in FID scores and 22 % higher entropy in generated data. This paper also discusses future directions, including quantum transformers, NISQ deployment, and cross-domain applications, positioning QINR-QGAN as a scalable bridge between quantum and classical AI.
One of the most promising applications in the era of Noisy Intermediate-Scale Quantum (NISQ) computing is quantum generative adversarial networks (QGANs), which offer significant quantum advantages over classical machine learning in various domains. However, QGANs suffer from mode collapse and lack explicit control over the features of generated outputs. To overcome these limitations, we propose InfoQGAN, a novel quantum-classical hybrid generative adversarial network that integrates the principles of InfoGAN with a QGAN architecture. Our approach employs a variational quantum circuit for data generation, a classical discriminator, and a Mutual Information Neural Estimator (MINE) to explicitly optimize the mutual information between latent codes and generated samples. Numerical simulations on synthetic 2D distributions and Iris dataset augmentation demonstrate that InfoQGAN effectively mitigates mode collapse while achieving robust feature disentanglement in the quantum generator. By leveraging these advantages, InfoQGAN not only enhances training stability but also improves data augmentation performance through controlled feature generation. These results highlight the potential of InfoQGAN as a foundational approach for advancing quantum generative modeling in the NISQ era.
Generative Adversarial Networks (GANs) have demonstrated immense potential in synthesizing diverse and high-fidelity images; however, critical questions remain regarding how quantum principles might best enhance their representational capacity. This thesis investigates hybrid quantum-classical GAN architectures supplemented by transfer learning in the discriminator, systematically examining whether incorporating Variational Quantum Circuits (VQCs) into the generator, the discriminator, or both improves performance over fully classical baselines. We evaluate each configuration using standard GAN benchmarks (CIFAR-10 classes: Birds, Cars, and Dogs) under varying sample sizes (5,000 vs. 2,500 images per class) to gauge both robustness and data efficiency. Our findings indicate that fully hybrid models, which incorporate VQCs in both the generator and the discriminator, consistently produce images of higher visual quality and achieve more favorable quantitative metrics (such as Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Inception Score (IS)) compared to their fully classical counterpart. In particular, VQCs in the generator accelerate early feature learning, whereas those in the discriminator, despite exhibiting slower initial convergence, ultimately facilitate more refined synthetic outputs. Moreover, the model sustains near-comparable performance even when the dataset size is halved, suggesting that transfer learning and quantum enhancements mitigate data limitations. By comparing classical and hybrid configurations in detail, this thesis illustrates the trade-offs arising from VQCs in GANs, such as variations in early-epoch convergence and final generative quality. Overall, the results underscore that carefully integrating quantum computing principles with classical adversarial training and pretrained feature extraction can significantly enrich GAN-based image synthesis. These insights open avenues for future work on higher-resolution tasks, alternative quantum circuit designs, and experimentation with emerging quantum hardware.
This paper introduces a novel hybrid quantumclassical model using QGAN (quantum generative adversarial network) to achieve more efficient, convergent and noiserobust machine learning for nearterm quantum (NISQ) applications. Unlike the existing GAN type models that were purely classical or purely quantum, to propose a quantum generator consisting of shallow variation circuits (48 qubits) together with a classical discriminator that is crucial for the stability of adversarial training. The empirical results on the MNIST dataset showed that were able to perform classification with an accuracy of 94.2%, an improvement of over 3.2% from a straightforward classical only approach, while NVGAN also improved its generative performance to a Fréchet Inception Distance (FID) score of 38.7 or 26% in quality enhancement from synthesis perspective. Both trainings converged 50 epochs earlier than each training when used the hybrid model (30% improvement in convergence). The key innovation of this work is bringing (1) to bear both the utility of the quantumenhanced feature representation to have at disposal, and (2) classical stability measures and erroraware optimizations (such as parameter clipping, early stopping), such that its hybridization enabled it to continue operating with>90%accuracy under cases of reasonable depolarizing/amplitude damping noise on an MLP where purely quantum formulations decayed to (approx 70%). Altogether, the paper validates the presented hybrid QGAN approach as a statistically substantiated noise robust and scalable representational tool for real world applications of quantum enhanced machine learning tasks on NISQ platforms.
With the speedy advancement of hardware, quantum machine learning has garnered widespread attention. Generative Adversarial Networks (GANs) are widely adopted quantum machine learning frameworks used for providing highstandard audio content, images, and videos. Utilizing quantum computing for image generation has been found to offer several potential advantages over non-quantum technologies. Current quantum Generative Adversarial Networks (QGANs) still face challenges, such as the inability to generate high-quality images. In the current investigation, we propose a QGAN model based on Autoencoders (BAE-QCGAN) and evaluate its performance. By drawing upon the entanglement and expression capabilities of quantum circuits, our composite system outperforms classical GANs in terms of Frechet Inception Distance, requiring fewer training parameters and fewer iterations to converge. We also demonstrate that BAEQCGAN outperforms another quantum GAN, the patch-GAN, and is adapted for existing Noisy Intermediate Scale Quantum (NISQ) computers.