Boundary-Seeking Generative Adversarial Networks

Generative adversarial networks (GANs) are a learning framework that rely on training a discriminator to estimate a measure of difference between a target and generated distributions. GANs, as normally formulated, rely on the generated samples being completely differentiable w.r.t. the generative parameters, and thus do not work for discrete data. We introduce a method for training GANs with discrete data that uses the estimated difference measure from the discriminator to compute importance weights for generated samples, thus providing a policy gradient for training the generator. The importance weights have a strong connection to the decision boundary of the discriminator, and we call our method boundary-seeking GANs (BGANs). We demonstrate the effectiveness of the proposed algorithm with discrete image and character-based natural language generation. In addition, the boundary-seeking objective extends to continuous data, which can be used to improve stability of training.

• Publication year

  2017

• Venue

  International Conference on Learning Representations

• Publication date

  2017-02-27

• Fields of study

  Mathematics, Computer Science

• Identifiers
  arXiv 1702.08431
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• GENERATIVE ADVERSARIAL NETS

  2018influential reference
• Adversarial Learning for Neural Dialogue Generation

  2017cited by this paper
• Towards Diverse and Natural Image Descriptions via a Conditional GAN

  2017cited by this paper
• Variational Inference using Implicit Distributions

  2017cited by this paper
• REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

  2017cited by this paper
• AdaGAN: Boosting Generative Models

  2017cited by this paper
• Maximum-Likelihood Augmented Discrete Generative Adversarial Networks

  2017cited by this paper
• BEGAN: Boundary Equilibrium Generative Adversarial Networks

  2017cited by this paper
• Deep and Hierarchical Implicit Models

  2017cited by this paper
• Improved Training of Wasserstein GANs

  2017influential reference
• McGan: Mean and Covariance Feature Matching GAN

  2017cited by this paper
• Hierarchical Implicit Models and Likelihood-Free Variational Inference

  2017cited by this paper
• Wasserstein GAN

  2017cited by this paper
• Parametric Adversarial Divergences are Good Task Losses for Generative Modeling

  2017cited by this paper
• Stabilizing Training of Generative Adversarial Networks through Regularization

  2017influential reference
• Adversarially Regularized Autoencoders for Generating Discrete Structures

  2017cited by this paper
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables

  2016cited by this paper
• Least Squares Generative Adversarial Networks

  2016cited by this paper
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

  2016influential reference
• On the Quantitative Analysis of Decoder-Based Generative Models

  2016cited by this paper
• NIPS 2016 Tutorial: Generative Adversarial Networks

  2016cited by this paper
• Categorical Reparameterization with Gumbel-Softmax

  2016influential reference
• Variational Inference for Monte Carlo Objectives

  2016cited by this paper
• Adversarially Learned Inference

  2016cited by this paper
• SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient

  2016cited by this paper
• Improved Techniques for Training GANs

  2016cited by this paper
• Professor Forcing: A New Algorithm for Training Recurrent Networks

  2016cited by this paper
• Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy

  2016cited by this paper
• Theano: A Python framework for fast computation of mathematical expressions

  2016cited by this paper
• Learning in Implicit Generative Models

  2016cited by this paper
• Simultaneous Deep Transfer Across Domains and Tasks

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Blocks and Fuel: Frameworks for deep learning

  2015cited by this paper
• LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop

  2015cited by this paper
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

  2015influential reference
• Deep Residual Learning for Image Recognition

  2015cited by this paper
• MuProp: Unbiased Backpropagation for Stochastic Neural Networks

  2015cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Deep Learning Face Attributes in the Wild

  2014influential reference
• Neural Variational Inference and Learning in Belief Networks

  2014cited by this paper
• Reweighted Wake-Sleep

  2014cited by this paper
• One billion word benchmark for measuring progress in statistical language modeling

  2013cited by this paper
• Auto-Encoding Variational Bayes

  2013influential reference
• Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Statistical Language Models Based on Neural Networks

  2012cited by this paper
• Reading Digits in Natural Images with Unsupervised Feature Learning

  2011influential reference
• Generating Text with Recurrent Neural Networks

  2011cited by this paper
• On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient

  2010cited by this paper
• On integral probability metrics, φ-divergences and binary classification

  2009cited by this paper
• Deep Boltzmann Machines

  2009cited by this paper
• Learning Multiple Layers of Features from Tiny Images

  2009cited by this paper
• On the quantitative analysis of deep belief networks

  2008cited by this paper
• Estimating Divergence Functionals and the Likelihood Ratio by Convex Risk Minimization

  2008cited by this paper
• Training Products of Experts by Minimizing Contrastive Divergence

  2002cited by this paper
• Mean Field Theory for Sigmoid Belief Networks

  1996cited by this paper
• The Helmholtz Machine

  1995cited by this paper
• Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper

  1977cited by this paper
• Statistical Theory of Extreme Values and Some Practical Applications : A Series of Lectures

  1954influential reference

• Generative Adversarial Networks for Modeling Bio-Electric Fields in Medicine: A Review of EEG, ECG, EMG, and EOG Applications

  2026cites this paper
• Research on Augmentation of Wood Microscopic Image Dataset Based on Generative Adversarial Networks

  2025cites this paper
• YOLO-Based Third-Rail Defect Detection With BGAN-Augmented Training

  2025cites this paper
• Dual Prototypes-Based Personalized Federated Adversarial Cross-Modal Hashing

  2025cites this paper
• FedRecon: Missing Modality Reconstruction in Heterogeneous Distributed Environments

  2025influential citation
• A dual-discriminator network based on Sobel gradient operator for digital twin-assisted fault diagnosis

  2025cites this paper
• AVP Prediction Research Based on Generative Networks

  2024cites this paper
• Super-Resolution Based ROI Enhancement Approaches for Palmprint Recognition

  2024cites this paper
• CCFN: Depression Detection via Multimodal Fusion with Complex-valued Capsule Network

  2024influential citation
• Generating Mental Health Transcripts with SAPE (Spanish Adaptive Prompt Engineering)

  2024cites this paper
• A Comparative Analysis of the Novel Conditional Deep Convolutional Neural Network Model, Using Conditional Deep Convolutional Generative Adversarial Network-Generated Synthetic and Augmented Brain Tumor Datasets for Image Classification

  2024cites this paper
• Guided Discrete Diffusion for Electronic Health Record Generation

  2024cites this paper
• IGAMT: Privacy-Preserving Electronic Health Record Synthesization with Heterogeneity and Irregularity

  2024cites this paper
• S2-DMs: Skip-Step Diffusion Models

  2024cites this paper
• DogLayout: Denoising Diffusion GAN for Discrete and Continuous Layout Generation

  2024cites this paper
• Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors

  2024cites this paper
• Latest Trends in Deep Learning Techniques for Image Steganography

  2023cites this paper
• Reinforcement Learning for Generative AI: A Survey

  2023cites this paper
• Infrared Image Transformation via Spatial Propagation Network

  2023cites this paper
• Deep Learning for Zero-day Malware Detection and Classification: A Survey

  2023cites this paper
• Privacy-Preserving Medical Data Generation Using Adversarial Learning

  2023cites this paper
• FoGGAN: Generating Realistic Parkinson’s Disease Freezing of Gait Data Using GANs

  2023cites this paper
• Boundary-Seeking GAN Approach to Improve Classification of Intrusion Detection Systems Based on Machine Learning Model

  2023cites this paper
• Applications of game theory in deep learning: a survey

  2022cites this paper
• Reducing Adversarial Vulnerability Using GANs

  2022cites this paper
• Implementing a Hierarchical Deep Learning Approach for Simulating Multilevel Auction Data

  2022cites this paper
• Patch Antenna Design using Artificial Intelligence Methods for 4G/5G Applications

  2022influential citation
• Improving detection of malicious samples by using state-of-the-art adversarial machine learning algorithms

  2022cites this paper
• A Survey of Defect Detection Applications Based on Generative Adversarial Networks

  2022cites this paper
• Composition Learning in “Modular” Robot Systems

  2022influential citation
• Artificial Intelligence for In Silico Clinical Trials: A Review

  2022cites this paper
• An Improved Intrusion Detection Systems using BGAN

  2022cites this paper
• Generative Adversarial Networks in Time Series: A Systematic Literature Review

  2022cites this paper
• Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning

  2022influential citation
• On Deep Generative Modeling in Economics: An Application with Public Procurement Data

  2022cites this paper
• CoupGAN: Chinese couplet generation via encoder–decoder model and adversarial training under global control

  2022cites this paper
• Modular Robot Design Optimization with Generative Adversarial Networks

  2022influential citation
• Generation of novel and diverse molecules using Self-attention Generative Adversarial Networks

  2022cites this paper
• A Survey of Generative Adversarial Networks for Synthesizing Structured Electronic Health Records

  2022cites this paper
• Tuberculosis Bacteria Detection and Counting in Fluorescence Microscopy Images Using a Multi-Stage Deep Learning Pipeline

  2022cites this paper
• Causal Imitation Learning With Unobserved Confounders

  2022cites this paper
• Generative Cooperative Networks for Natural Language Generation

  2022cites this paper
• RGAN: Rényi Generative Adversarial Network

  2021cites this paper
• Few-Shot Adaptive Detection of Objects of Concern Using Generative Models with Negative Retraining

  2021cites this paper
• Generating synthetic mixed-type longitudinal electronic health records for artificial intelligent applications

  2021cites this paper
• EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

  2021cites this paper
• Review of machine learning‐driven design of polymer‐based dielectrics

  2021cites this paper
• Comparison of generative adversarial networks architectures for biomedical images synthesis

  2021cites this paper
• OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary

  2021cites this paper
• Data Anonymization for Pervasive Health Care: Systematic Literature Mapping Study

  2021cites this paper
• Deep Neural Networks and Tabular Data: A Survey

  2021cites this paper
• GAN models in natural language processing and image translation

  2021cites this paper
• Deep learning analysis based on multi-sensor fusion data for hemiplegia rehabilitation training system for stoke patients

  2021cites this paper
• Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging

  2021cites this paper
• Unaligned Image-to-Image Translation by Learning to Reweight

  2021cites this paper
• Beyond Simple Images: Human Knowledge-Guided GANs for Clinical Data Generation

  2021cites this paper
• Generative adversarial networks in time series: A survey and taxonomy

  2021cites this paper
• Product innovation concept generation based on deep learning and Kansei engineering

  2021cites this paper
• A survey on text generation using generative adversarial networks

  2021influential citation
• Prb-GAN: A Probabilistic Framework for GAN Modelling

  2021cites this paper
• Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review

  2021influential citation
• 3D Carbonate Digital Rock Reconstruction Using Progressive Growing GAN

  2021cites this paper
• Improving Training of Generative Adversarial Networks

  2021influential citation
• Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluation

  2021cites this paper
• Designing mm-wave electromagnetic engineered surfaces using generative adversarial networks

  2021cites this paper
• Spectrum of Advancements and Developments in Multidisciplinary Domains for Generative Adversarial Networks (GANs)

  2021cites this paper
• Training Generative Adversarial Networks in One Stage

  2021cites this paper
• Neural Language Generation: Formulation, Methods, and Evaluation

  2020cites this paper
• GANsDTA: Predicting Drug-Target Binding Affinity Using GANs

  2020cites this paper
• A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications

  2020cites this paper
• COR-GAN: Correlation-Capturing Convolutional Neural Networks for Generating Synthetic Healthcare Records

  2020cites this paper
• Residential Load Data Generation

  2020cites this paper
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

  2020cites this paper
• Learning Generative Models using Transformations

  2020cites this paper
• CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records

  2020cites this paper
• Early prediction for mode anomaly in generative adversarial network training: An empirical study

  2020cites this paper
• A Survey on Generative Adversarial Networks: Variants, Applications, and Training

  2020cites this paper
• Cumulant GAN

  2020cites this paper
• High-dimensional cluster boundary detection using directed Markov tree

  2020cites this paper
• Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models

  2020cites this paper
• Generative Augmented Dataset and Annotation Frameworks for Artificial Intelligence (GADAFAI)

  2020cites this paper
• Fast Multi-Focus Ultrasound Image Recovery Using Generative Adversarial Networks

  2020influential citation
• Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE

  2020cites this paper
• An Intelligent Maritime Communication Signal Recognition Algorithm based on ACWGAN

  2020cites this paper
• Semi-Supervised Adversarial Variational Autoencoder

  2020cites this paper
• Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer

  2020cites this paper
• Automatic vertebrae recognition from arbitrary spine MRI images by a category-Consistent self-calibration detection framework

  2020cites this paper
• Boundary Of Distribution Support Generator (BDSG): Sample Generation On The Boundary

  2020cites this paper
• GRL: Knowledge graph completion with GAN-based reinforcement learning

  2020cites this paper
• Synthetic Observational Health Data with GANs: from slow adoption to a boom in medical research and ultimately digital twins?

  2020influential citation
• Tail of Distribution GAN (TailGAN): GenerativeAdversarial-Network-Based Boundary Formation

  2020cites this paper
• Synthetic data augmentation for surface defect detection and classification using deep learning

  2020cites this paper
• Differentially Private Synthetic Medical Data Generation using Convolutional GANs

  2020cites this paper
• Imbalanced Process Fault Diagnosis Using Enhanced Auxiliary Classifier GAN

  2020cites this paper
• KLIEP-based Density Ratio Estimation for Semantically Consistent Synthetic to Real Images Adaptation in Urban Traffic Scenes

  2020cites this paper
• Visual Reconstruction of Ancient Coins Using Cycle-Consistent Generative Adversarial Networks

  2020cites this paper
• ReshapeGAN: Object Reshaping by Providing A Single Reference Image

  2019cites this paper
• A Research on Generative Adversarial Networks Applied to Text Generation

  2019cites this paper
• GAN-based Generation and Automatic Selection of Explanations for Neural Networks

  2019cites this paper
• The Six Fronts of the Generative Adversarial Networks

  2019cites this paper