scholarly journals A Deep Generative Model for Code Switched Text

2019 ◽  
Author(s):  
Bidisha Samanta ◽  
Sharmila Reddy ◽  
Hussain Jagirdar ◽  
Niloy Ganguly ◽  
Soumen Chakrabarti
Keyword(s):  
State Of The Art ◽  
Generative Models ◽  
Code Switching ◽  
Language Models ◽  
Generative Adversarial Networks ◽  
Data Intensive ◽  
Adversarial Networks ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Multilingual Societies

Code-switching, the interleaving of two or more languages within a sentence or discourse is pervasive in multilingual societies. Accurate language models for code-switched text are critical for NLP tasks. State-of-the-art data-intensive neural language models are difficult to train well from scarce language-labeled code-switched text. A potential solution is to use deep generative models to synthesize large volumes of realistic code-switched text. Although generative adversarial networks and variational autoencoders can synthesize plausible monolingual text from continuous latent space, they cannot adequately address code-switched text, owing to their informal style and complex interplay between the constituent languages. We introduce VACS, a novel variational autoencoder architecture specifically tailored to code-switching phenomena. VACS encodes to and decodes from a two-level hierarchical representation, which models syntactic contextual signals in the lower level, and language switching signals in the upper layer. Sampling representations from the prior and decoding them produced well-formed, diverse code-switched sentences. Extensive experiments show that using synthetic code-switched text with natural monolingual data results in significant (33.06\%) drop in perplexity.

Synthesizing Designs With Interpart Dependencies Using Hierarchical Generative Adversarial Networks

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Wei Chen ◽  
Mark Fuge
Keyword(s):  
Constraint Satisfaction ◽  
Real World ◽  
Generative Models ◽  
Dependency Graph ◽  
Generative Adversarial Networks ◽  
Engineering Systems ◽  
Adversarial Networks ◽  
Latent Space ◽  
Branching Factor ◽  
Low Dimensional

Abstract Real-world designs usually consist of parts with interpart dependencies, i.e., the geometry of one part is dependent on one or multiple other parts. We can represent such dependency in a part dependency graph. This paper presents a method for synthesizing these types of hierarchical designs using generative models learned from examples. It decomposes the problem of synthesizing the whole design into synthesizing each part separately but keeping the interpart dependencies satisfied. Specifically, this method constructs multiple generative models, the interaction of which is based on the part dependency graph. We then use the trained generative models to synthesize or explore each part design separately via a low-dimensional latent representation, conditioned on the corresponding parent part(s). We verify our model on multiple design examples with different interpart dependencies. We evaluate our model by analyzing the constraint satisfaction performance, the synthesis quality, the latent space quality, and the effects of part dependency depth and branching factor. This paper’s techniques for capturing dependencies among parts lay the foundation for learned generative models to extend to more realistic engineering systems where such relationships are widespread.

scholarly journals LOGAN: Membership Inference Attacks Against Generative Models

2019 ◽  
Vol 2019 (1) ◽  
pp. 133-152 ◽  
Author(s):  
Jamie Hayes ◽  
Luca Melis ◽  
George Danezis ◽  
Emiliano De Cristofaro
Keyword(s):  
Diabetic Retinopathy ◽  
State Of The Art ◽  
Generative Models ◽  
Black Box ◽  
Mitigation Strategies ◽  
Generative Adversarial Networks ◽  
Underlying Distribution ◽  
Target Model ◽  
Adversarial Networks ◽  
Inference Attacks

Abstract Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data point, the adversary determines whether or not it was used to train the model. Our attacks leverage Generative Adversarial Networks (GANs), which combine a discriminative and a generative model, to detect overfitting and recognize inputs that were part of training datasets, using the discriminator’s capacity to learn statistical differences in distributions. We present attacks based on both white-box and black-box access to the target model, against several state-of-the-art generative models, over datasets of complex representations of faces (LFW), objects (CIFAR-10), and medical images (Diabetic Retinopathy). We also discuss the sensitivity of the attacks to different training parameters, and their robustness against mitigation strategies, finding that defenses are either ineffective or lead to significantly worse performances of the generative models in terms of training stability and/or sample quality.

scholarly journals Improvement of Learning Stability of Generative Adversarial Network Using Variational Learning

2020 ◽  
Vol 10 (13) ◽  
pp. 4528
Author(s):  
Je-Yeol Lee ◽  
Sang-Il Choi 
Keyword(s):  
Generative Models ◽  
Learning Processes ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Secondary Network ◽  
Variational Autoencoder ◽  
Variational Learning

In this paper, we propose a new network model using variational learning to improve the learning stability of generative adversarial networks (GAN). The proposed method can be easily applied to improve the learning stability of GAN-based models that were developed for various purposes, given that the variational autoencoder (VAE) is used as a secondary network while the basic GAN structure is maintained. When the gradient of the generator vanishes in the learning process of GAN, the proposed method receives gradient information from the decoder of the VAE that maintains gradient stably, so that the learning processes of the generator and discriminator are not halted. The experimental results of the MNIST and the CelebA datasets verify that the proposed method improves the learning stability of the networks by overcoming the vanishing gradient problem of the generator, and maintains the excellent data quality of the conventional GAN-based generative models.

scholarly journals Disentangled Face Attribute Editing via Instance-Aware Latent Space Search

2021 ◽  
Author(s):  
Yuxuan Han ◽  
Jiaolong Yang ◽  
Ying Fu
Keyword(s):  
Optimal Control ◽  
State Of The Art ◽  
Attribute Level ◽  
Generative Adversarial Networks ◽  
Control Factor ◽  
Training Set ◽  
Wide Margin ◽  
Adversarial Networks ◽  
Latent Space ◽  
Model Complex

Recent works have shown that a rich set of semantic directions exist in the latent space of Generative Adversarial Networks (GANs), which enables various facial attribute editing applications. However, existing methods may suffer poor attribute variation disentanglement, leading to unwanted change of other attributes when altering the desired one. The semantic directions used by existing methods are at attribute level, which are difficult to model complex attribute correlations, especially in the presence of attribute distribution bias in GAN's training set. In this paper, we propose a novel framework (IALS) that performs Instance-Aware Latent-Space Search to find semantic directions for disentangled attribute editing. The instance information is injected by leveraging the supervision from a set of attribute classifiers evaluated on the input images. We further propose a Disentanglement-Transformation (DT) metric to quantify the attribute transformation and disentanglement efficacy and find the optimal control factor between attribute-level and instance-specific directions based on it. Experimental results on both GAN-generated and real-world images collectively show that our method outperforms state-of-the-art methods proposed recently by a wide margin. Code is available at https://github.com/yxuhan/IALS.

scholarly journals Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness

2021 ◽  
Author(s):  
Dazhong Shen ◽  
Chuan Qin ◽  
Chao Wang ◽  
Hengshu Zhu ◽  
Enhong Chen ◽  
...  
Keyword(s):  
Latent Variables ◽  
State Of The Art ◽  
Likelihood Estimation ◽  
Generative Models ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
Latent Representations ◽  
Low Uncertainty

As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. However, when the decoder network is sufficiently expressive, VAE may lead to posterior collapse; that is, uninformative latent representations may be learned. To this end, in this paper, we propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space, and thus the representation can be learned in a meaningful and compact manner. Specifically, we first theoretically demonstrate that it will result in better latent space with high diversity and low uncertainty awareness by controlling the distribution of posterior’s parameters across the whole data accordingly. Then, without the introduction of new loss terms or modifying training strategies, we propose to exploit Dropout on the variances and Batch-Normalization on the means simultaneously to regularize their distributions implicitly. Furthermore, to evaluate the generalization effect, we also exploit DU-VAE for inverse autoregressive flow based-VAE (VAE-IAF) empirically. Finally, extensive experiments on three benchmark datasets clearly show that our approach can outperform state-of-the-art baselines on both likelihood estimation and underlying classification tasks.

Synthesizing Designs With Inter-Part Dependencies Using Hierarchical Generative Adversarial Networks

2018 ◽  
Author(s):  
Wei Chen ◽  
Ashwin Jeyaseelan ◽  
Mark Fuge
Keyword(s):  
Real World ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Design Exploration ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Latent Space ◽  
Latent Representations

Real-world designs usually consist of parts with hierarchical dependencies, i.e., the geometry of one component (a child shape) is dependent on another (a parent shape). We propose a method for synthesizing this type of design. It decomposes the problem of synthesizing the whole design into synthesizing each component separately but keeping the inter-component dependencies satisfied. This method constructs a two-level generative adversarial network to train two generative models for parent and child shapes, respectively. We then use the trained generative models to synthesize or explore parent and child shapes separately via a parent latent representation and infinite child latent representations, each conditioned on a parent shape. We evaluate and discuss the disentanglement and consistency of latent representations obtained by this method. We show that shapes change consistently along any direction in the latent space. This property is desirable for design exploration over the latent space.

scholarly journals OptAGAN: Entropy-based Finetuning on Text VAE-GAN

2021 ◽  
Author(s):  
Paolo Tirotta ◽  
Stefano Lodi
Keyword(s):  
Language Processing ◽  
Generative Adversarial Networks ◽  
Word Generation ◽  
Adversarial Networks ◽  
Current State ◽  
Latent Space ◽  
Variational Autoencoder ◽  
Maximum Likelihood Methods ◽  
High Level

Transfer learning through large pre-trained models has changed the landscape of current applications in natural language processing (NLP). Recently Optimus, a variational autoencoder (VAE) which combines two pre-trained models, BERT and GPT-2, has been released, and its combination with generative adversarial networks (GANs) has been shown to produce novel, yet very human-looking text. The Optimus and GANs combination avoids the troublesome application of GANs to the discrete domain of text, and prevents the exposure bias of standard maximum likelihood methods. We combine the training of GANs in the latent space, with the finetuning of the decoder of Optimus for single word generation. This approach lets us model both the high-level features of the sentences, and the low-level word-by-word generation. We finetune using reinforcement learning (RL) by exploiting the structure of GPT-2 and by adding entropy-based intrinsically motivated rewards to balance between quality and diversity. We benchmark the results of the VAE-GAN model, and show the improvements brought by our RL finetuning on three widely used datasets for text generation, with results that greatly surpass the current state-of-the-art for the quality of the generated texts.

scholarly journals Fast and Accurate Electromagnetic and Hadronic Showers from Generative Models

2021 ◽  
Vol 251 ◽  
pp. 03049
Author(s):  
Erik Buhmann ◽  
Sascha Diefenbacher ◽  
Engin Eren ◽  
Frank Gaede ◽  
Daniel Hundhausen ◽  
...  
Keyword(s):  
Particle Physics ◽  
Computational Cost ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Event Simulation ◽  
Information Bottleneck ◽  
Adversarial Networks ◽  
Latent Space ◽  
High Computational Cost ◽  
Expected Increase

Generative machine learning models offer a promising way to efficiently amplify classical Monte Carlo generators’ statistics for event simulation and generation in particle physics. Given the already high computational cost of simulation and the expected increase in data in the high-precision era of the LHC and at future colliders, such fast surrogate simulators are urgently needed. This contribution presents a status update on simulating particle showers in high granularity calorimeters for future colliders. Building on prior work using Generative Adversarial Networks (GANs), Wasserstein-GANs, and the information-theoretically motivated Bounded Information Bottleneck Autoencoder (BIB-AE), we further improve the fidelity of generated photon showers. The key to this improvement is a detailed understanding and optimisation of the latent space. The richer structure of hadronic showers compared to electromagnetic ones makes their precise modeling an important yet challenging problem. We present initial progress towards accurately simulating the core of hadronic showers in a highly granular scintillator calorimeter.

scholarly journals An Overview of Variational Autoencoders for Source Separation, Finance, and Bio-Signal Applications

Entropy ◽  
2021 ◽  
Vol 24 (1) ◽  
pp. 55
Author(s):  
Aman Singh ◽  
Tokunbo Ogunfunmi
Keyword(s):  
Input Data ◽  
Source Separation ◽  
Generative Models ◽  
Learning System ◽  
Generative Adversarial Networks ◽  
Space Representation ◽  
Comprehensive Overview ◽  
Maximum Information ◽  
Adversarial Networks ◽  
Latent Space

Autoencoders are a self-supervised learning system where, during training, the output is an approximation of the input. Typically, autoencoders have three parts: Encoder (which produces a compressed latent space representation of the input data), the Latent Space (which retains the knowledge in the input data with reduced dimensionality but preserves maximum information) and the Decoder (which reconstructs the input data from the compressed latent space). Autoencoders have found wide applications in dimensionality reduction, object detection, image classification, and image denoising applications. Variational Autoencoders (VAEs) can be regarded as enhanced Autoencoders where a Bayesian approach is used to learn the probability distribution of the input data. VAEs have found wide applications in generating data for speech, images, and text. In this paper, we present a general comprehensive overview of variational autoencoders. We discuss problems with the VAEs and present several variants of the VAEs that attempt to provide solutions to the problems. We present applications of variational autoencoders for finance (a new and emerging field of application), speech/audio source separation, and biosignal applications. Experimental results are presented for an example of speech source separation to illustrate the powerful application of variants of VAE: VAE, β-VAE, and ITL-AE. We conclude the paper with a summary, and we identify possible areas of research in improving performance of VAEs in particular and deep generative models in general, of which VAEs and generative adversarial networks (GANs) are examples.

Generative Adversarial Networks (GANs)

2021 ◽  
Vol 54 (3) ◽  
pp. 1-42
Author(s):  
Divya Saxena ◽  
Jiannong Cao
Keyword(s):  
Optimization Technique ◽  
Generative Models ◽  
Generative Adversarial Networks ◽  
Network Architectures ◽  
Research Directions ◽  
Research Issues ◽  
Design And Optimization ◽  
Adversarial Networks ◽  
Comprehensive Survey ◽  
Selection Of

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.

Sign in / Sign up

Export Citation Format

Share Document