JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets

Abstract

A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional distributions between the domains, while simultaneously learning to sample from the marginals of each individual domain. The proposed framework consists of multiple generators and a single softmax-based critic, all jointly trained via adversarial learning. From a simple noise source, the proposed framework allows synthesis of draws from the marginals, conditional draws given observations from a subset of random variables, or complete draws from the full joint distribution. Most examples considered are for joint analysis of two domains, with examples for three domains also presented.

arXiv commentAccepted by ICML 2018

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Adversarial Feature Learning
• Adversarially Learned Inference
• Autoencoding beyond pixels using a learned similarity metric
• Invertible Conditional GANs for image editing
• Variational Autoencoder for Deep Learning of Images, Labels and Captions
• DualGAN: Unsupervised Dual Learning for Image-to-Image Translation
• Triple Generative Adversarial Nets
• AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks
• Adversarial Feature Matching for Text Generation
• Generative Visual Manipulation on the Natural Image Manifold
• Learning Generic Sentence Representations Using Convolutional Neural Networks

Cited by in corpus (9)

• Triple Generative Adversarial Networks
• Causal Adversarial Network for Learning Conditional and Interventional Distributions
• Training Generative Adversarial Networks from Incomplete Observations using Factorised Discriminators
• Multivariate-Information Adversarial Ensemble for Scalable Joint Distribution Matching
• Generative Adversarial Data Programming
• Facial Emotion Recognition with Noisy Multi-task Annotations
• G3AN: Disentangling Appearance and Motion for Video Generation
• EMIXER: End-to-end Multimodal X-ray Generation via Self-supervision
• Hierarchical Modes Exploring in Generative Adversarial Networks