Review of Quantum Generative Adversarial Networks

Ashish Solanki, Sandeep Singh Kang, Sanjay Singla

Images are a very useful form of information from medical diagnosis to scientific discovery. There are some areas where images are not enough but with the help of Generative Adversarial Networks (GANs) this problem is solved at some limit. Due to the success of classical generative adversarial networks, the quantum researcher created quantum version of GAN and also called as quantum generative adversarial network (QGANs) which works on quantum computers which use quantum mechanics techniques such as quantum entanglement, superposition, teleportation and many more. The successful implementation in real life of quantum computers are not easy because of limited quantum resources and access to quantum processors but instead of that there are different QGAN models for different purpose, such as drug discovery, finance, image generation and many more which shown good result as compare to their classical counterparts. This study is reviewed based on authors that proposed different QGAN models along with the techniques proposed on those papers for generating images, which datasets was considered, which parameters are considered, what their limitations and how to future research directions to overcome those problems.

Satyadhyan Chickerur, Vasavi Kumbargeri

Tong Li, Shibin Zhang, Jinyue Xia

Generative adversarial network (GAN) is one of the most promising methods for unsupervised learning in recent years. GAN works via adversarial training concept and has shown excellent performance in the fields image synthesis, image super-resolution, video generation, image translation, etc. Compared with classical algorithms, quantum algorithms have their unique advantages in dealing with complex tasks, quantum machine learning (QML) is one of the most promising quantum algorithms with the rapid development of quantum technology. Specifically, Quantum generative adversarial network (QGAN) has shown the potential exponential quantum speedups in terms of performance. Meanwhile, QGAN also exhibits some problems, such as barren plateaus, unstable gradient, model collapse, absent complete scientific evaluation system, etc. How to improve the theory of QGAN and apply it that have attracted some researcher. In this paper, we comprehensively and deeply review recently proposed GAN and QAGN models and their applications, and we discuss the existing problems and future research trends of QGAN.

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

Wael Maged Badawy

Hybrid Quantum Generative Adversarial Networks (HQ-GANs) have emerged as a promising class of models at the intersection of quantum computing and generative artificial intelligence. Unlike early quantum generative approaches that relied on fully quantum pipelines, hybrid QGANs combine parameterized quantum circuits with classical optimization and discrimination mechanisms, enabling practical training under the constraints of noisy intermediate-scale quantum (NISQ) hardware. This paper presents a comprehensive technical review of hybrid QGAN architectures, with a particular focus on implicit quantum representations and hybrid optimization strategies that enhance expressivity, stability, and scalability. We analyze how recent advances in variational circuit design, data re-encoding, Wasserstein-based objectives, and hybriddepth control have reshaped the feasibility of quantum generative learning. New mathematical formulations are introduced to describe implicit quantum mappings and hybrid adversarial convergence. Comparative analysis highlights performance trends, architectural trade-offs, and unresolved challenges related to noise, barren plateaus, and hardware–software mismatch. The paper concludes by outlining future research directions toward robust, application-ready quantum generative intelligence.

Murphy Yuezhen Niu, Michael Broughton, Alexander Zlokapa +3 more