The demand for artificially generated data for the development, training and testing of new algorithms is omnipresent. Quantum computing (QC), does offer the hope that its inherent probabilistic functionality can be utilised in this field of generative artificial intelligence. In this study, we use quantum-classical hybrid generative adversarial networks (QuGANs) to artificially generate graphs of shipping routes. We create a training dataset based on real shipping data and investigate to what extent QuGANs are able to learn and reproduce inherent distributions and geometric features of this data. We compare hybrid QuGANs with classical Generative Adversarial Networks (GANs), with a special focus on their parameter efficiency. Our results indicate that QuGANs are indeed able to quickly learn and represent underlying geometric properties and distributions, although they seem to have difficulties in introducing variance into the sampled data. Compared to classical GANs of greater size, measured in the number of parameters used, some QuGANs show similar result quality. Our reference to concrete use cases, such as the generation of shipping data, provides an illustrative example and demonstrate the potential and diversity in which QC can be used.
The demand for artificially generated data for the development, training and testing of new algorithms is omnipresent. Quantum computing (QC), does offer the hope that its inherent probabilistic functionality can be utilised in this field of generative artificial intelligence. In this study, we use quantum-classical hybrid generative adversarial networks (QuGANs) to artificially generate graphs of shipping routes. We create a training dataset based on real shipping data and investigate to what extent QuGANs are able to learn and reproduce inherent distributions and geometric features of this data. We compare hybrid QuGANs with classical Generative Adversarial Networks (GANs), with a special focus on their parameter efficiency. Our results indicate that QuGANs are indeed able to quickly learn and represent underlying geometric properties and distributions, although they seem to have difficulties in introducing variance into the sampled data. Compared to classical GANs of greater size, measured in the number of parameters used, some QuGANs show similar result quality. Our reference to concrete use cases, such as the generation of shipping data, provides an illustrative example and demonstrate the potential and diversity in which QC can be used.
Abstract Generative Adversarial Networks (GANs) have revolutionized Deep learning-based generative models are still challenging to train. This is due to issues such as mode collapse, instability, and non-convergence. This article provides a comprehensive analysis of the challenges faced by classical GANs, offering insights into their computational flow and limitations. Additionally, it explores Quantum Generative Adversarial Networks (QuGANs), detailing their unique architecture and the mechanism of quantum information generation. To further advance the field, this work presents an in-depth analysis of a hybridized model combining classical GANs and QuGANs, leveraging the strengths of both paradigms to enhance learning and stability. Furthermore, a novel algorithm for training quantum–classical GANs is proposed, with a detailed complexity analysis to assess its computational efficiency. The integration of quantum principles into classical frameworks offers a promising direction to mitigate existing GANs limitations while unlocking new possibilities for quantum machine learning. The proposed approach aims to bridge the gap between classical and quantum generative models, improving training dynamics and sample quality. The objective of this investigation is to establish a foundation for improving the efficiency and comprehension of hybrid GANs architectures, which will allow the design of more efficient and durable generative models in quantum computing.
Quantum computers have the potential to outperform classical counterparts by leveraging quantum algorithms; however, achieving this advantage requires the efficient encoding of generic data representations into qubit states. Hybrid Quantum-Classical Generative Adversarial Networks (qGANs) have shown potential for learning generic probability distributions from real datasets and loading them efficiently into qubits. This work extends previous approaches to qGANs by implementing a configurable framework for generating multidimensional datasets with specific distributions, training hybrid qGANS to reproduce those distributions, and evaluating the performance of the trained model. The framework supports the configuration of multiple loss functions. In the paper, we evaluate the framework by comparing the training performance when using Binary Cross-Entropy (BCE) and Wasserstein distance as loss functions during the training of qGANS on one, two, and three-dimensional datasets with different distributions. The paper paves the way for future experimental research on implementing efficient quantum machine learning algorithms based on properties of the Wasserstein distance.
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.
Tremendous progress has been witnessed in artificial intelligence, where neural network backed deep learning systems have been used, with applications in almost every domain. As a representative deep learning framework, Generative Adversarial Network (GAN) has been widely used for generating artificial images, text-to-image or image augmentation across areas of science, arts and video games. However, GANs are computationally expensive, sometimes computationally prohibitive. Furthermore, training GANs may suffer from convergence failure and modal collapse. Aiming at the acceleration of use cases for practical quantum computers, we propose QuGAN, a quantum GAN architecture that provides stable convergence, quantum-states based gradients and significantly reduced parameter sets. The QuGANarchitecture runs both the discriminator and the generator purely on quantum state fidelity and utilizes the swap test on qubits to calculate the values of quantum-based loss functions. Built on quantum layers, QuGAN achieves similar performance with a 94.98% reduction on the parameter set when compared to classical GANs. With the same number of parameters, addition-ally, QuGAN outperforms state-of-the-art quantum based GANsin the literature providing a 48.33% improvement in system performance compared to others attaining less than 0.5% in terms of similarity between generated distributions and original data sets.
Quantum mechanics studies nature and its behavior at the scale of atoms and subatomic particles. By applying quantum mechanics, a lot of problems can be solved in a more convenient way thanks to its special quantum properties, such as superposition and entanglement. In the current noisy intermediate-scale quantum era, quantum mechanics finds its use in various fields of life. Following this trend, researchers seek to augment machine learning in a quantum way. The generative adversarial network (GAN), an important machine learning invention that excellently solves generative tasks, has also been extended with quantum versions. Since the first publication of a quantum GAN (QuGAN) in 2018, many QuGAN proposals have been suggested. A QuGAN may have a fully quantum or a hybrid quantum–classical architecture, which may need additional data processing in the quantum–classical interface. Similarly to classical GANs, QuGANs are trained using a loss function in the form of max likelihood, Wasserstein distance, or total variation. The gradients of the loss function can be calculated by applying the parameter-shift method or a linear combination of unitaries in order to update the parameters of the networks. In this paper, we review recent advances in quantum GANs. We discuss the structures, optimization, and network evaluation strategies of QuGANs. Different variants of quantum GANs are presented in detail.
Quantum machine learning (QML) has received increasing attention due to its potential to outperform classical machine learning methods in problems such as classification and identification tasks. A subclass of QML methods is quantum generative adversarial networks (QGANs) which have been studied as a quantum counterpart of classical GANs widely used in image manipulation and generation tasks. The existing work on QGANs is still limited to small-scale proof-of-concept examples based on images with significant down-scaling. Here we integrate classical and quantum techniques to propose a new hybrid quantum-classical GAN framework. We demonstrate its superior learning capabilities over existing quantum techniques by generating 28×28 pixels grey-scale images without dimensionality reduction or classical pre/post-processing on multiple classes of the standard MNIST and Fashion MNIST datasets, which achieves comparable results to classical frameworks with three orders of magnitude less trainable generator parameters. To gain further insight into the working of our hybrid approach, we systematically explore the impact of its parameter space by varying the number of qubits, the size of image patches, the number of layers in the generator, the shape of the patches and the choice of prior distribution. Our results show that increasing the quantum generator size generally improves the learning capability of the network. The developed framework provides a foundation for future design of QGANs with optimal parameter set tailored for complex image generation tasks