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

Lecture notes in computer science

Towards Stable and Diverse Generative Models with Dual Hybrid Quantum Generative Adversarial Network

S. Kushal Varma, Maski Yashasv, Lanka Dhanush, Kotari Harshith, Srinath Devale

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.1007/978-3-032-26352-0_32

Related papers

Exponential capacity scaling of classical GANs compared to hybrid latent style-based quantum GANs

Milan Liepelt, Julien Baglio

Quantum generative modeling is a very active area of research in looking for practical advantage in data analysis. Quantum generative adversarial networks (QGANs) are leading candidates for quantum generative modeling and have been applied to diverse areas, from high-energy physics to image generation. The latent style-based QGAN, relying on a classical variational autoencoder to encode the input data into a latent space and then using a style-based QGAN for data generation has been proven to be efficient for image generation or drug design, hinting at the use of far less trainable parameters than their classical counterpart to achieve comparable performance, however this advantage has never been systematically studied. We present in this work the first comprehensive experimental analysis of this advantage of QGANS applied to SAT4 image generation, obtaining an exponential advantage in capacity scaling for a quantum generator in the hybrid latent style-based QGAN architecture. Careful tuning of the autoencoder is crucial to obtain stable, reliable results. Once this tuning is performed and defining training optimality as when the training is stable and the FID score is low and stable as well, the optimal capacity (or number of trainable parameters) of the classical discriminator scales exponentially with respect to the capacity of the quantum generator, and the same is true for the capacity of the classical generator. This hints toward a type of quantum advantage for quantum generative modeling.

quant-pharXiv:2601.05036•Jan 9, 2026•0 citations

Quantum Generative Adversarial Networks

Satyadhyan Chickerur, Vasavi Kumbargeri

Algorithms for intelligent systems•Jan 1, 2022•5 citations

Unrolled generative adversarial network for continuous distributions under hybrid quantum-classical model

Chen Gong, Zhuo-Yu Wen, Yun-Wei Deng +2 more

Abstract Quantum generative adversarial networks (QGANs) can effectively enhance the performance and efficiency of classical GANs by utilizing the parallelism of quantum computation and quantum superposition. However, QGANs typically suffer from mode collapse during the training process of generative tasks. It would make the generator only be able to generate partially correct data approximately. To solve this problem, an unrolled QGAN model based on a hybrid quantum-classical framework is constructed. The unrolled QGAN can match the generator with a better discriminator by separately training the discriminator prior to the training on the generator. The model is applied to generate quantum and Gaussian distributions, and comparative experiments are performed between the QGAN and the proposed unrolled one. Mean value, KL divergence, and standard deviation are calculated and compared to evaluate the generative performance of the model. Numerical and experimental results show that the proposed unrolled QGAN can increase the diversity and coverage of generated data distributions, significantly enhancing the generative effect.

Laser Physics Letters•Nov 1, 2024•4 citations

Review of Quantum Generative Adversarial Networks

Xinghao Jia, Yi Zheng, Shuang Ren

Lecture notes in electrical engineering•Jan 1, 2026•0 citations

Applications and experimental realizations of quantum generative adversarial networks

Seth Lloyd, Giacomo De Palma, Bobak T. Kiani +1 more

Bulletin of the American Physical Society•Mar 19, 2021•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
Quantum generative modeling is a very active area of research in looking for practical advantage in data analysis. Quantum generative adversarial networks (QGANs) are leading candidates for quantum generative modeling and have been applied to diverse areas, from high-energy physics to image generation. The latent style-based QGAN, relying on a classical variational autoencoder to encode the input data into a latent space and then using a style-based QGAN for data generation has been proven to be efficient for image generation or drug design, hinting at the use of far less trainable parameters than their classical counterpart to achieve comparable performance, however this advantage has never been systematically studied. We present in this work the first comprehensive experimental analysis of this advantage of QGANS applied to SAT4 image generation, obtaining an exponential advantage in capacity scaling for a quantum generator in the hybrid latent style-based QGAN architecture. Careful tuning of the autoencoder is crucial to obtain stable, reliable results. Once this tuning is performed and defining training optimality as when the training is stable and the FID score is low and stable as well, the optimal capacity (or number of trainable parameters) of the classical discriminator scales exponentially with respect to the capacity of the quantum generator, and the same is true for the capacity of the classical generator. This hints toward a type of quantum advantage for quantum generative modeling.
Abstract Quantum generative adversarial networks (QGANs) can effectively enhance the performance and efficiency of classical GANs by utilizing the parallelism of quantum computation and quantum superposition. However, QGANs typically suffer from mode collapse during the training process of generative tasks. It would make the generator only be able to generate partially correct data approximately. To solve this problem, an unrolled QGAN model based on a hybrid quantum-classical framework is constructed. The unrolled QGAN can match the generator with a better discriminator by separately training the discriminator prior to the training on the generator. The model is applied to generate quantum and Gaussian distributions, and comparative experiments are performed between the QGAN and the proposed unrolled one. Mean value, KL divergence, and standard deviation are calculated and compared to evaluate the generative performance of the model. Numerical and experimental results show that the proposed unrolled QGAN can increase the diversity and coverage of generated data distributions, significantly enhancing the generative effect.
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.