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.

Download Full-text

Conditional generative models for sampling and phase transition indication in spin systems

SciPost Physics ◽

10.21468/scipostphys.11.2.043 ◽

2021 ◽

Vol 11 (2) ◽

Author(s):

Japneet Singh ◽

Mathias Scheurer ◽

Vipul Arora

Keyword(s):

Generative Models ◽

Training Data ◽

Generative Adversarial Networks ◽

Xy Model ◽

Network Architectures ◽

Learning Approaches ◽

Tuning Parameters ◽

Adversarial Networks ◽

Detailed Evaluation ◽

Fidelity Measure

In this work, we study generative adversarial networks (GANs) as a tool to learn the distribution of spin configurations and to generate samples, conditioned on external tuning parameters or other quantities associated with individual configurations. For concreteness, we focus on two examples of conditional variables---the temperature of the system and the energy of the samples. We show that temperature-conditioned models can not only be used to generate samples across thermal phase transitions, but also be employed as unsupervised indicators of transitions. To this end, we introduce a GAN-fidelity measure that captures the model’s susceptibility to external changes of parameters. The proposed energy-conditioned models are integrated with Monte Carlo simulations to perform over-relaxation steps, which break the Markov chain and reduce auto-correlations. We propose ways of efficiently representing the physical states in our network architectures, e.g., by exploiting symmetries, and to minimize the correlations between generated samples. A detailed evaluation, using the two-dimensional XY model as an example, shows that these incorporations bring in considerable improvements over standard machine-learning approaches. We further study the performance of our architectures when no training data is provided near the critical region.

Download Full-text

Best Selection of Generative Adversarial Networks Hyper-Parameters using Genetic Algorithm

10.21203/rs.3.rs-95571/v1 ◽

2020 ◽

Author(s):

Fajr Alarsan ◽

Mamoon Younes

Keyword(s):

Genetic Algorithm ◽

Programming Language ◽

Loss Function ◽

Generative Adversarial Networks ◽

Accuracy Function ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Adversarial Networks ◽

Parameters Selection ◽

Selection Of

Abstract Generative Adversarial Networks (GANs) are most popular generative frameworks that have achieved compelling performance. They follow an adversarial approach where two deep models generator and discriminator compete with each other In this paper, we propose a Generative Adversarial Network with best hyper-parameters selection to generate fake images for digits number 1 to 9 with generator and train discriminator to decide whereas the generated images are fake or true. Using Genetic Algorithm technique to adapt GAN hyper-parameters, the final method is named GANGA:Generative Adversarial Network with Genetic Algorithm. Anaconda environment with tensorflow library facilitates was used, python as programming language also used with needed libraries. The implementation was done using MNIST dataset to validate our work. The proposed method is to let Genetic algorithm to choose best values of hyper-parameters depending on minimizing a cost function such as a loss function or maximizing accuracy function. GA was used to select values of Learning rate, Batch normalization, Number of neurons and a parameter of Dropout layer.

Download Full-text

Conditional Wasserstein Generative Adversarial Networks for Fast Detector Simulation

EPJ Web of Conferences ◽

10.1051/epjconf/202125103055 ◽

2021 ◽

Vol 251 ◽

pp. 03055

Author(s):

John Blue ◽

Braden Kronheim ◽

Michelle Kuchera ◽

Raghuram Ramanujan

Keyword(s):

High Energy Physics ◽

High Energy ◽

Generative Models ◽

Generative Adversarial Networks ◽

Detector Response ◽

Event Simulation ◽

Simulation Process ◽

Adversarial Networks ◽

Wide Range ◽

Detector Simulation

Detector simulation in high energy physics experiments is a key yet computationally expensive step in the event simulation process. There has been much recent interest in using deep generative models as a faster alternative to the full Monte Carlo simulation process in situations in which the utmost accuracy is not necessary. In this work we investigate the use of conditional Wasserstein Generative Adversarial Networks to simulate both hadronization and the detector response to jets. Our model takes the 4-momenta of jets formed from partons post-showering and pre-hadronization as inputs and predicts the 4-momenta of the corresponding reconstructed jet. Our model is trained on fully simulated tt events using the publicly available GEANT-based simulation of the CMS Collaboration. We demonstrate that the model produces accurate conditional reconstructed jet transverse momentum (pT) distributions over a wide range of pT for the input parton jet. Our model takes only a fraction of the time necessary for conventional detector simulation methods, running on a CPU in less than a millisecond per event.

Download Full-text

InvNet: Encoding Geometric and Statistical Invariances in Deep Generative Models

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.5863 ◽

2020 ◽

Vol 34 (04) ◽

pp. 4377-4384

Author(s):

Ameya Joshi ◽

Minsu Cho ◽

Viraj Shah ◽

Balaji Pokuri ◽

Soumik Sarkar ◽

...

Keyword(s):

Image Data ◽

Generative Models ◽

Generative Adversarial Networks ◽

Complex Data ◽

Challenging Problem ◽

Two Phase ◽

Adversarial Networks ◽

Generative Modeling ◽

Lack Of Control ◽

Real World Problems

Generative Adversarial Networks (GANs), while widely successful in modeling complex data distributions, have not yet been sufficiently leveraged in scientific computing and design. Reasons for this include the lack of flexibility of GANs to represent discrete-valued image data, as well as the lack of control over physical properties of generated samples. We propose a new conditional generative modeling approach (InvNet) that efficiently enables modeling discrete-valued images, while allowing control over their parameterized geometric and statistical properties. We evaluate our approach on several synthetic and real world problems: navigating manifolds of geometric shapes with desired sizes; generation of binary two-phase materials; and the (challenging) problem of generating multi-orientation polycrystalline microstructures.

Download Full-text

Learning Generative Adversarial Networks from Multiple Data Sources

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/391 ◽

2019 ◽

Cited By ~ 2

Author(s):

Trung Le ◽

Quan Hoang ◽

Hung Vu ◽

Tu Dinh Nguyen ◽

Hung Bui ◽

...

Keyword(s):

Generative Models ◽

Data Sources ◽

Black Hair ◽

Primary Data ◽

Generative Adversarial Networks ◽

Auxiliary Data ◽

Adversarial Networks ◽

Multiple Data ◽

Data Source ◽

Push And Pull

Generative Adversarial Networks (GANs) are a powerful class of deep generative models. In this paper, we extend GAN to the problem of generating data that are not only close to a primary data source but also required to be different from auxiliary data sources. For this problem, we enrich both GANs' formulations and applications by introducing pushing forces that thrust generated samples away from given auxiliary data sources. We term our method Push-and-Pull GAN (P2GAN). We conduct extensive experiments to demonstrate the merit of P2GAN in two applications: generating data with constraints and addressing the mode collapsing problem. We use CIFAR-10, STL-10, and ImageNet datasets and compute Fréchet Inception Distance to evaluate P2GAN's effectiveness in addressing the mode collapsing problem. The results show that P2GAN outperforms the state-of-the-art baselines. For the problem of generating data with constraints, we show that P2GAN can successfully avoid generating specific features such as black hair.

Download Full-text

Emulation of Cosmological Mass Maps with Conditional Generative Adversarial Networks

Frontiers in Artificial Intelligence ◽

10.3389/frai.2021.673062 ◽

2021 ◽

Vol 4 ◽

Author(s):

Nathanaël Perraudin ◽

Sandro Marcon ◽

Aurelien Lucchi ◽

Tomasz Kacprzak

Keyword(s):

Gravitational Lensing ◽

Cosmological Parameters ◽

Similarity Index ◽

Power Spectra ◽

Generative Models ◽

Generative Adversarial Networks ◽

Summary Statistics ◽

Redshift Distribution ◽

Adversarial Networks ◽

The Universe

Weak gravitational lensing mass maps play a crucial role in understanding the evolution of structures in the Universe and our ability to constrain cosmological models. The prediction of these mass maps is based on expensive N-body simulations, which can create a computational bottleneck for cosmological analyses. Simulation-based emulators of map summary statistics, such as the matter power spectrum and its covariance, are starting to play increasingly important role, as the analytical predictions are expected to reach their precision limits for upcoming experiments. Creating an emulator of the cosmological mass maps themselves, rather than their summary statistics, is a more challenging task. Modern deep generative models, such as Generative Adversarial Networks (GAN), have demonstrated their potential to achieve this goal. Most existing GAN approaches produce simulations for a fixed value of the cosmological parameters, which limits their practical applicability. We propose a novel conditional GAN model that is able to generate mass maps for any pair of matter density Ωm and matter clustering strength σ8, parameters which have the largest impact on the evolution of structures in the Universe, for a given source galaxy redshift distribution n(z). Our results show that our conditional GAN can interpolate efficiently within the space of simulated cosmologies, and generate maps anywhere inside this space with good visual quality high statistical accuracy. We perform an extensive quantitative comparison of the N-body and GAN -generated maps using a range of metrics: the pixel histograms, peak counts, power spectra, bispectra, Minkowski functionals, correlation matrices of the power spectra, the Multi-Scale Structural Similarity Index (MS-SSIM) and our equivalent of the Fréchet Inception Distance. We find a very good agreement on these metrics, with typical differences are <5% at the center of the simulation grid, and slightly worse for cosmologies at the grid edges. The agreement for the bispectrum is slightly worse, on the <20% level. This contribution is a step toward building emulators of mass maps directly, capturing both the cosmological signal and its variability. We make the code1 and the data2 publicly available.

Download Full-text

Deep image synthesis from intuitive user input: A review and perspectives

Computational Visual Media ◽

10.1007/s41095-021-0234-8 ◽

2021 ◽

Vol 8 (1) ◽

pp. 3-31

Author(s):

Yuan Xue ◽

Yuan-Chen Guo ◽

Han Zhang ◽

Tao Xu ◽

Song-Hai Zhang ◽

...

Keyword(s):

Image Synthesis ◽

Generative Models ◽

Generative Adversarial Networks ◽

Image Generation ◽

Art And Design ◽

User Input ◽

Adversarial Networks ◽

Benchmark Datasets ◽

Deep Image ◽

Realistic Images

AbstractIn many applications of computer graphics, art, and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph, or layout, and have a computer system automatically generate photo-realistic images according to that input. While classically, works that allow such automatic image content generation have followed a framework of image retrieval and composition, recent advances in deep generative models such as generative adversarial networks (GANs), variational autoencoders (VAEs), and flow-based methods have enabled more powerful and versatile image generation approaches. This paper reviews recent works for image synthesis given intuitive user input, covering advances in input versatility, image generation methodology, benchmark datasets, and evaluation metrics. This motivates new perspectives on input representation and interactivity, cross fertilization between major image generation paradigms, and evaluation and comparison of generation methods.

Download Full-text

Deep learning in bioinformatics: introduction, application, and perspective in big data era

10.1101/563601 ◽

2019 ◽

Cited By ~ 9

Author(s):

Yu Li ◽

Chao Huang ◽

Lizhong Ding ◽

Zhongxiao Li ◽

Yijie Pan ◽

...

Keyword(s):

Neural Networks ◽

Big Data ◽

Deep Learning ◽

Generative Adversarial Networks ◽

Great Success ◽

Research Directions ◽

Adversarial Networks ◽

Variational Autoencoder ◽

The Common ◽

Graph Neural Networks

AbstractDeep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics. With the advances of the big data era in biology, it is foreseeable that deep learning will become increasingly important in the field and will be incorporated in vast majorities of analysis pipelines. In this review, we provide both the exoteric introduction of deep learning, and concrete examples and implementations of its representative applications in bioinformatics. We start from the recent achievements of deep learning in the bioinformatics field, pointing out the problems which are suitable to use deep learning. After that, we introduce deep learning in an easy-to-understand fashion, from shallow neural networks to legendary convolutional neural networks, legendary recurrent neural networks, graph neural networks, generative adversarial networks, variational autoencoder, and the most recent state-of-the-art architectures. After that, we provide eight examples, covering five bioinformatics research directions and all the four kinds of data type, with the implementation written in Tensorflow and Keras. Finally, we discuss the common issues, such as overfitting and interpretability, that users will encounter when adopting deep learning methods and provide corresponding suggestions. The implementations are freely available at https://github.com/lykaust15/Deep_learning_examples.

Download Full-text

CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesis

10.1115/detc2021-68103 ◽

2021 ◽

Author(s):

Amin Heyrani Nobari ◽

Muhammad Fathy Rashad ◽

Faez Ahmed

Keyword(s):

Novelty Detection ◽

Computational Design ◽

Generative Models ◽

Machine Learning Techniques ◽

Generative Adversarial Networks ◽

Creative Design ◽

Design Synthesis ◽

Adversarial Networks ◽

Automated Method ◽

Learning Techniques

Abstract Modern machine learning techniques, such as deep neural networks, are transforming many disciplines ranging from image recognition to language understanding, by uncovering patterns in big data and making accurate predictions. They have also shown promising results for synthesizing new designs, which is crucial for creating products and enabling innovation. Generative models, including generative adversarial networks (GANs), have proven to be effective for design synthesis with applications ranging from product design to metamaterial design. These automated computational design methods can support human designers, who typically create designs by a time-consuming process of iteratively exploring ideas using experience and heuristics. However, there are still challenges remaining in automatically synthesizing ‘creative’ designs. GAN models, however, are not capable of generating unique designs, a key to innovation and a major gap in AI-based design automation applications. This paper proposes an automated method, named CreativeGAN, for generating novel designs. It does so by identifying components that make a design unique and modifying a GAN model such that it becomes more likely to generate designs with identified unique components. The method combines state-of-art novelty detection, segmentation, novelty localization, rewriting, and generative models for creative design synthesis. Using a dataset of bicycle designs, we demonstrate that the method can create new bicycle designs with unique frames and handles, and generalize rare novelties to a broad set of designs. Our automated method requires no human intervention and demonstrates a way to rethink creative design synthesis and exploration. For details and code used in this paper please refer to http://decode.mit.edu/projects/creativegan/.

Download Full-text

Generative adversarial networks for generating synthetic features for Wi-Fi signal quality

PLoS ONE ◽

10.1371/journal.pone.0260308 ◽

2021 ◽

Vol 16 (11) ◽

pp. e0260308

Author(s):

Mauro Castelli ◽

Luca Manzoni ◽

Tatiane Espindola ◽

Aleš Popovič ◽

Andrea De Lorenzo

Keyword(s):

Synthetic Data ◽

Real Data ◽

Generative Models ◽

Generative Adversarial Networks ◽

Signal Quality ◽

Quality Service ◽

High Quality ◽

The Real ◽

Adversarial Networks ◽

High Quality Service

Wireless networks are among the fundamental technologies used to connect people. Considering the constant advancements in the field, telecommunication operators must guarantee a high-quality service to keep their customer portfolio. To ensure this high-quality service, it is common to establish partnerships with specialized technology companies that deliver software services in order to monitor the networks and identify faults and respective solutions. A common barrier faced by these specialized companies is the lack of data to develop and test their products. This paper investigates the use of generative adversarial networks (GANs), which are state-of-the-art generative models, for generating synthetic telecommunication data related to Wi-Fi signal quality. We developed, trained, and compared two of the most used GAN architectures: the Vanilla GAN and the Wasserstein GAN (WGAN). Both models presented satisfactory results and were able to generate synthetic data similar to the real ones. In particular, the distribution of the synthetic data overlaps the distribution of the real data for all of the considered features. Moreover, the considered generative models can reproduce the same associations observed for the synthetic features. We chose the WGAN as the final model, but both models are suitable for addressing the problem at hand.

Download Full-text