Generative Adversarial Networks Variants Research Articles

Challenges of Using Synthetic Data Generation Methods for Tabular Microdata

The generation of synthetic data holds significant promise for augmenting limited datasets while avoiding privacy issues, facilitating research, and enhancing machine learning models’ robustness. Generative Adversarial Networks (GANs) stand out as promising tools, employing two neural networks—generator and discriminator—to produce synthetic data that mirrors real data distributions. This study evaluates GAN variants (CTGAN, CopulaGAN), a variational autoencoder, and copulas on diverse real datasets of different complexity encompassing numerical and categorical attributes. The results highlight CTGAN’s sensitivity to training parameters and TVAE’s robustness across datasets. Scalability challenges persist, with GANs demanding substantial computational resources. TVAE stands out for its high utility across all datasets, even for high-dimensional data, though it incurs higher privacy risks, which is indicative of the curse of dimensionality. While no single model universally excels, understanding the trade-offs and leveraging model strengths can significantly enhance synthetic data generation (SDG). Future research should focus on adaptive learning mechanisms, scalability enhancements, and standardized evaluation metrics to advance SDG methods effectively. Addressing these challenges will foster broader adoption and application of synthetic data.

Garbage In [formula omitted] Garbage Out: Exploring GAN Resilience to Image Training Set Degradations

Generative Adversarial Networks (GANs) have received immense attention in recent years due to their ability to capture complex, high-dimensional data distributions without the need for extensive labeling. Since their conception in 2014, a wide array of GAN variants have been proposed featuring alternative architectures, optimizers, and loss functions with the goal of improving performance and training stability. This manuscript focuses on quantifying the resilience of a GAN architecture to specific modes of image degradation. We conduct systematic experimentation to empirically determine the effects of 10 fundamental image degradation modes, applied to the training image dataset, on the Fréchet inception distance (FID) of images generated by a conditional deep convolutional GAN (cDCGAN). We find that at the α=0.05 level, brightening, darkening, and blurring are statistically significantly more detrimental to the resulting GAN image quality than removing the degraded data completely, while other degradations are typically safe to keep in training datasets. Additionally, we find that in the case of randomized partial occlusion, the FID of the resulting GAN images approaches that of the degraded training set for increasing levels of occlusion, with the surprising result that GAN FID performance is equal to that of the training set at 75% degradation.

Gradient Boosting classifier performance evaluation using Generative Adversarial Networks

Increasing amount of cyber-attacks in past few years have necessitated the development of automatic threat detection systems for ensuring network and data security. Such automated threat detection models for handling cyber threats are subjected to adversarial attacks. Developing such robust detection models resilient to the attacks require rigorous training and testing with ample number of adversarial examples (AEs) prior to deployment in real-world scenarios where the models are subjected tothe new and unseen data and attacks. Generating adversarial examples with Generative Adversarial Networks (GANs) and its variants is a widely adopted technique. While many notable works generate adversarial examples using the confidence scores of the features that require extensive knowledge about the underlying features of the dataset. This work focuses on generating adversarial examples using Wasserstein condition generative adversarial network and analyzing the robustness of several Gradient-boosted classifiers namely, Adaptive boosting classifier, Categorical Boosting Classifier and Light gradient-boosting classifier on the synthetic and real data. A comparison is also made in the process of generating synthetic data with both GANs and Confidence scores on benchmark dataset NSL-KDD. The robustness of Gradient-boosted classifiers Adaboost, Catboost and LightGBM are tested with these generated data that claim for the superiority of variants of GAN over Confidence scores using features.

Stock market forecasting using DRAGAN and feature matching

Applying machine learning methods to forecast stock prices has been a topic of interest in recent years. However, a few studies have been reported based on generative adversarial networks (GANs) in this area, but their results are promising. While GANs are powerful generative models successfully applied in different areas, they suffer from inherent challenges such as training instability and mode collapse. Another primary concern is capturing correlations in stock prices. Therefore, the main challenges fall into two categories: capturing correlations and addressing the inherent problems of GANs. In this paper, we introduce a novel framework based on DRAGAN11Deep Regret Analytic Generative Adversarial Network. and feature matching for stock price forecasting, which improves training stability and alleviates mode collapse. We employ windowing to acquire temporal correlations by the generator and exploit conditioning on discriminator inputs to capture temporal correlations and correlations between prices and features. Experimental results on data from several stocks indicate that proposed method outperforms long short-term memory (LSTM) as a baseline method, as well as basic GANs and WGAN-GP22Wasserstein GAN – Gradient Penalty. as two different variants of GANs.

Time-series generative adversarial networks for flood forecasting

Reliable flood forecasting serves as one of the fundamental tasks in flood management. However, the forecast performance of modern data-driven models depends heavily on the quantity and quality of training data. The lack of field data of flood events highly underpins the development of machine learning (ML) flood forecasting techniques. With consideration of the rareness of flood events and the high dimensionality of flood time series, two latest variants of generative adversarial networks (GANs), Time-series Generative Adversarial Network (TimeGAN) and Real-world Time Series Generative Adversarial Network (RTSGAN), were applied to generate synthetic flood timeseries. In the example analysis of the Xijiang River Basin in southern China, results show that time-series GANs can accurately and efficiently mimic the spatiotemporal correlations between flood series from multiple sites, and RTSGAN outperforms TimeGAN especially when the lengths of time series are long. Additionally, gradient boosting regression tree (GBRT), long-short term memory (LSTM) and quantile regression method integrated LSTM networks (QRLSTM) flood forecasting models were trained with real sequences and an extra amount of synthetic sequences. It shows that the expansion of training datasets in this way is promising in reducing prediction errors of classical machine learning models. In the 3-day-ahead flood forecast, the introduction of synthetic training datasets has little positive effect on both GBRT and LSTM. In 24-hour-ahead flood forecast, as the lead period increases, GBRT-RTSGAN outperforms GBRT evidenced by a 6.7% increase in Nash-Sutcliffe efficiency (NSE) metric, a 56.5% reduction in average absolute relative error (AARE) metric and a 33.1% reduction in root-mean square error (RMSE) metric. For interval forecast, the use of synthetic training datasets helps QRLSTM obtain lower prediction interval normalized averaged width (PINAW), however, at the cost of prediction interval coverage probability (PICP).

A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been proposed. Nevertheless, few comprehensive studies explain the connections among different GAN variants and how they have evolved. In this paper, we attempt to provide a review of the various GAN methods from the perspectives of algorithms, theory, and applications. First, the motivations, mathematical representations, and structures of most GAN algorithms are introduced in detail, and we compare their commonalities and differences. Second, theoretical issues related to GANs are investigated. Finally, typical applications of GANs in image processing and computer vision, natural language processing, music, speech and audio, the medical field, and data science are discussed.

A Survey on GAN Techniques for Data Augmentation to Address the Imbalanced Data Issues in Credit Card Fraud Detection

Data augmentation is an important procedure in deep learning. GAN-based data augmentation can be utilized in many domains. For instance, in the credit card fraud domain, the imbalanced dataset problem is a major one as the number of credit card fraud cases is in the minority compared to legal payments. On the other hand, generative techniques are considered effective ways to rebalance the imbalanced class issue, as these techniques balance both minority and majority classes before the training. In a more recent period, Generative Adversarial Networks (GANs) are considered one of the most popular data generative techniques as they are used in big data settings. This research aims to present a survey on data augmentation using various GAN variants in the credit card fraud detection domain. In this survey, we offer a comprehensive summary of several peer-reviewed research papers on GAN synthetic generation techniques for fraud detection in the financial sector. In addition, this survey includes various solutions proposed by different researchers to balance imbalanced classes. In the end, this work concludes by pointing out the limitations of the most recent research articles and future research issues, and proposes solutions to address these problems.

Quantification of similarity and physical awareness of microstructures generated via generative models

Large repositories of microstructure realizations lie at the centre of developing effective structure–property correlations in materials. It is, however important that the microstructure generation procedures not only reconstruct a large number of microstructures in a computationally inexpensive manner but also hold awareness regarding the physical significance of the underlying microstructure. While machine learning techniques are used for computationally efficient microstructure generation, the similarity and physical awareness of the generated microstructures with the ground truth are rarely quantified. In this work, we use a variant of generative adversarial network (GAN) i.e. StyleGAN2, to generate microstructures with varied morphologies from a small dataset of Dual Phase (DP) steels. The similarity between the generated and the original microstructures is quantified using various metrics such as structure similarity index (SSIM), peak signal to noise ratio (PSNR) and signal to noise ratio (SNR). The physical awareness is quantified by comparing the predictions of macroscopic mechanical properties of the GAN generated and original microstructures using a reduced order model. We also qualitatively estimate the learning of the GAN latent space in terms of microstructure morphology. It is observed that there exists a relationship between the microstructure morphological information and the similarity assessment metrics.

Face Generation Using General Adversial Networks

Face generation is a difficult task with numerous uses in security (for example, creating portraits from descriptions), styling, and entertainment. In this study, we investigate generating faces conditioned on identification using modifications to generative adversarial networks (GANs). In the realm of artificial intelligence, deep learning has had significant success, and several deep learning models have been created. One of the deep learning models, Generative Adversarial Networks (GAN), which was proposed based on zero-sum game theory and has become a new research hotspot. The importance of the GAN model variation is to provide more accurate and realistic data by using unsupervised learning to obtain the data distribution. Due to their vast potential for use in areas including language processing, video processing, and image and vision computing, GANs are currently the subject of extensive research. This project introduces the history of the GAN, theoretical models, and extensional variants of GANs, where the variants can either modify the fundamental structures of the original GAN or further optimise it. The typical uses of GANs are then described. Finally, a summary of the current GAN issues and a description of the models' upcoming work are provided.

A Deep Exposition of GAN and its applications

Generative Adversarial Networks (GANs) have revolutionized the field of machine learning and artificial intelligence by providing a powerful framework for generating realistic and high-quality synthetic data. GANs consist of two networks, a generator that produces synthetic data and a discriminator that distinguishes between the synthetic data and real data. The two networks are trained together in a game-theoretic setting, where the generator tries to produce synthetic data that is similar to the real data, while the discriminator tries to distinguish between the two. This paper provides a deep exposition of GAN and its applications, starting with the basics of GANs, their architecture, and how they work. We then discuss the training process of GAN, the challenges associated with it, and the techniques used to address these issues. We also describe the different variants of GANs, including conditional GAN, progressive GAN, and style-based GAN, and their applications. Next, we provide a comprehensive overview of the various domains where GANs have been successfully applied, such as image and video synthesis, text generation, and music composition. We discuss the potential future directions of GANs and their applications, including research areas that need further investigation. Finally, we highlight the challenges and limitations associated with GANs, such as mode collapse, vanishing gradients, and instability, and the ethical and legal issues associated with their applications. We conclude by summarizing the key points of the paper and highlighting the potential of GANs as a tool for generating realistic and high-quality synthetic data.

A literature review: Generative adversarial networks for civil structural health monitoring

Structural Health Monitoring (SHM) of civil structures has been constantly evolving with novel methods, advancements in data science, and more accessible technology to address issues related to structural safety, operations, and resiliency. Research and development in the civil SHM field during the last few decades have been progressive due to the increasing use of Artificial Intelligence (AI) methods such as Machine Learning (ML) and Deep Learning (DL). Particularly, Generative Adversarial Networks (GAN), which is a subfamily of Deep Learning has been highly favored in the SHM community within the last couple of years. After its release in 2014, GANs (original GAN and other GAN variants) have been in use for a wide variety of applications in various disciplines, and it has been one of the most popular research topics in the AI-ML domain. While there has not been a review study on the applications of GAN in the civil SHM field, this paper aims to fill this gap by presenting a literature review of the studies that employed GAN specifically in civil SHM applications from 2014 to date, in a condensed format. This study intends to inform SHM practitioners and researchers about GANs and present the highlights of the published work on GANs in the civil SHM field.

Analysis of AI-Based Single-View 3D Reconstruction Methods for an Industrial Application.

Machine learning (ML) is a key technology in smart manufacturing as it provides insights into complex processes without requiring deep domain expertise. This work deals with deep learning algorithms to determine a 3D reconstruction from a single 2D grayscale image. The potential of 3D reconstruction can be used for quality control because the height values contain relevant information that is not visible in 2D data. Instead of 3D scans, estimated depth maps based on a 2D input image can be used with the advantage of a simple setup and a short recording time. Determining a 3D reconstruction from a single input image is a difficult task for which many algorithms and methods have been proposed in the past decades. In this work, three deep learning methods, namely stacked autoencoder (SAE), generative adversarial networks (GANs) and U-Nets are investigated, evaluated and compared for 3D reconstruction from a 2D grayscale image of laser-welded components. In this work, different variants of GANs are tested, with the conclusion that Wasserstein GANs (WGANs) are the most robust approach among them. To the best of our knowledge, the present paper considers for the first time the U-Net, which achieves outstanding results in semantic segmentation, in the context of 3D reconstruction tasks. Unlike the U-Net, which uses standard convolutions, the stacked dilated U-Net (SDU-Net) applies stacked dilated convolutions. Of all the 3D reconstruction approaches considered in this work, the SDU-Net shows the best performance, not only in terms of evaluation metrics but also in terms of computation time. Due to the comparably small number of trainable parameters and the suitability of the architecture for strong data augmentation, a robust model can be generated with only a few training data.

Generative Adversarial Networks

Abstract: Deep learning's breakthrough in the field of artificial intelligence has resulted in the creation of a slew of deep learning models. One of these is the Generative Adversarial Network, which has only recently emerged. The goal of GAN is to use unsupervised learning to analyse the distribution of data and create more accurate results. The GAN allows the learning of deep representations in the absence of substantial labelled training information. Computer vision, language and video processing, and image synthesis are just a few of the applications that might benefit from these representations. The purpose of this research is to get the reader conversant with the GAN framework as well as to provide the background information on Generative Adversarial Networks, including the structure of both the generator and discriminator, as well as the various GAN variants along with their respective architectures. Applications of GANs are also discussed with examples. Keywords: Generative Adversarial Networks (GANs), Generator, Discriminator, Supervised and Unsupervised Learning, Discriminative and Generative Modelling, Backpropagation, Loss Functions, Machine Learning, Deep Learning, Neural Networks, Convolutional Neural Network (CNN), Deep Convolutional GAN (DCGAN), Conditional GAN (cGAN), Information Maximizing GAN (InfoGAN), Stacked GAN (StackGAN), Pix2Pix, Wasserstein GAN (WGAN), Progressive Growing GAN (ProGAN), BigGAN, StyleGAN, CycleGAN, Super-Resolution GAN (SRGAN), Image Synthesis, Image-to-Image Translation.

Generative Adversarial Networks (GANs)

Generative Adversarial Networks (GANs) is a novel class of deep generative models that has recently gained significant attention. GANs learn complex and high-dimensional distributions implicitly over images, audio, and data. However, there exist major challenges in training of GANs, i.e., mode collapse, non-convergence, and instability, due to inappropriate design of network architectre, use of objective function, and selection of optimization algorithm. Recently, to address these challenges, several solutions for better design and optimization of GANs have been investigated based on techniques of re-engineered network architectures, new objective functions, and alternative optimization algorithms. To the best of our knowledge, there is no existing survey that has particularly focused on the broad and systematic developments of these solutions. In this study, we perform a comprehensive survey of the advancements in GANs design and optimization solutions proposed to handle GANs challenges. We first identify key research issues within each design and optimization technique and then propose a new taxonomy to structure solutions by key research issues. In accordance with the taxonomy, we provide a detailed discussion on different GANs variants proposed within each solution and their relationships. Finally, based on the insights gained, we present promising research directions in this rapidly growing field.

Abstract No. 597 Improved perceived image quality and operator comfort when interpreting DynaCT images using variants of super resolution generative adversarial networks

Purpose is to improve perceived image quality and operator comfort when interpreting DynaCT images, we propose using variants of super resolution generative adversarial networks (GANs). Based on multiple factors of image acquisition, DynaCT images can have less perceived image quality than desired by human observers and interpreters even if these images may still contain all necessary diagnostic information at the spatial and contrast resolutions at which they are collected. Therefore, in order to improve perceived image quality and operator comfort when interpreting DynaCT images, we propose using variants of super resolution generative adversarial networks (GANs) in order to improve the perceptual quality of DynaCT images. We utilized multiple public versions of super resolution GANs that are available for local download on GitHub such as ESRGAN. We will also use a public repository of CT images (the CHAOS dataset) in order to train our own super resolution GAN variants. These variants of super resolution GANs will then be applied to locally collected DynaCT data and our research team will review the images for perceptual quality and neural network induced artifacts. All optimized images were subjectively perceived as of higher quality and higher resolution by two independent interpreting radiologists. There CT images had findings that were better visualized on optimized images including fistula formation for an abscess evaluation, additional arterial supply and, hepatic venous structures. Diagnostic CT’s and MRI diagnosed showed these findings before the procedure. Perceived image quality and operator comfort of DynaCT images could be increased using super resolution generative adversarial networks (GANs).

Automatic Detection of Melanins and Sebums from Skin Images Using a Generative Adversarial Network

Melanins and sebums are two important criteria for the quality evaluation of skin, and they are capable of providing customized suggestions for skin care. Currently, their detection is heavily relied on manual process performed by specialists in laboratory. Although efficient, such a manual detection is an expensive and labor-intensive procedure, and hence, there has been great interest in developing computational models for automatic detection of melanins and sebums from skin images. In this work, we propose an automatic detection algorithm, namely DAME, to identify these two kinds of substances based on a generative adversarial network (GAN). To do so, DAME makes use of a variant of GAN, i.e., pix2pix, due to its strength in image generation by learning the structural and contextual information of melanins and sebums observed from skin images. With these additional augmented images, a robust U-Net model can be learned for automatically detecting and marking melanins and sebums. To evaluate the performance of DAME, we have conducted a series of experiments by comparing it with several existing algorithms on real image datasets, and the results have demonstrated that DAME yields a substantially better detection accuracy than previously published algorithms in terms of several independent evaluation metrics. Moreover, DAME is believed to be more robust than other algorithms, as it obtains the smallest variance for each metric. Hence, DAME makes it possible to automatically detect melanins and sebums with a promising performance. Due to the strong learning ability of GAN, DAME is also able to identify melanins and sebums that are possibly ignored by specialists. The source codes of DAME and datasets used in the experiments are available at https://github.com/reBioco-der/DAME .

Challenges and Corresponding Solutions of Generative Adversarial Networks (GANs): A Survey Study

Generative Adversarial Networks (GANs) are an innovative class of deep learning generative model that has been popular among academics recently. GANs are able to learn distributions on complex high-dimensional data which made it efficient in images and audio processing. Nevertheless, in the training of GANs, some major challenges exist namely mode collapse, non-convergence, and instability. In recent years, in order to overcome these challenges, researchers have proposed many variants of GANs by redesigning network architecture, changing the form of objective functions, and altering optimization algorithms. In this research, we conducted a comprehensive investigation on the progress of GANs design and optimization solutions. Finally, according to the classification method, we provided a problem-solving structure to solve conquer the GANs training challenges.

The theoretical research of generative adversarial networks: an overview

Generative adversarial networks (GAN) has received great attention and made great progress since its emergence in 2014. In this paper, we focus on the theoretical achievements of GAN and discuss them in detail for readers who wish to know more about GAN. Based on the number of the implemented network architectures, we category the improved methods into two groups: GAN variants, which are composed of two networks, to improve the performance by adding some regularization to the loss function; hybrid GANs, which are usually combined with other generative models to improve the training stability. For GAN variants, we discuss the theoretical results of the distribution divergence, training dynamics and various improved methods. For hybrid GANs, we introduce the improved methods of combining encoder, autoencoder or VAE. We also cover some other important issues, such as the quantify metrics of generated samples and the basic construction structure. In addition, we discuss the advantages of the GAN over other deep generative models, the future directions worthy of study, as well as the open issues that the community should further address.

On oversampling imbalanced data with deep conditional generative models

Class imbalanced datasets are common in real-world applications ranging from credit card fraud detection to rare disease diagnosis. Recently, deep generative models have proved successful for an array of machine learning problems such as semi-supervised learning, transfer learning, and recommender systems. However their application to class imbalance situations is limited. In this paper, we consider class conditional variants of generative adversarial networks and variational autoencoders and apply them to the imbalance problem. The main question we seek to answer is whether or not deep conditional generative models can effectively learn the distributions of minority classes so as to produce synthetic observations that ultimately lead to improvements in the performance of a downstream classifier. The numerical results show that this is indeed true and that deep generative models outperform traditional oversampling methods in many circumstances, especially in cases of severe imbalance.

Improving Multi-Agent Generative Adversarial Nets with Variational Latent Representation.

Generative adversarial networks (GANs), which are a promising type of deep generative network, have recently drawn considerable attention and made impressive progress. However, GAN models suffer from the well-known problem of mode collapse. This study focuses on this challenge and introduces a new model design, called the encoded multi-agent generative adversarial network (E-MGAN), which tackles the mode collapse problem by introducing the variational latent representations learned from a variable auto-encoder (VAE) to a multi-agent GAN. The variational latent representations are extracted from training data to replace the random noise input of the general multi-agent GANs. The generator in E-MGAN employs multiple generators and is penalized by a classifier. This integration guarantees that the proposed model not only enhances the quality of generated samples but also improves the diversity of generated samples to avoid the mode collapse problem. Moreover, extensive experiments are conducted on both a synthetic dataset and two large-scale real-world datasets. The generated samples are visualized for qualitative evaluation. The inception score (IS) and Fréchet inception distance (FID) are adopted to measure the performance of the model for quantitative assessment. The results confirmed that the proposed model achieves outstanding performances compared to other state-of-the-art GAN variants.