Graphical Generative Adversarial Networks

04/10/2018
by   Chongxuan Li, et al.
0

We propose Graphical Generative Adversarial Networks (Graphical-GAN) to model structured data. Graphical-GAN conjoins the power of Bayesian networks on compactly representing the dependency structures among random variables and that of generative adversarial networks on learning expressive dependency functions. We introduce a structured recognition model to infer the posterior distribution of latent variables given observations. We propose two alternative divergence minimization approaches to learn the generative model and recognition model jointly. The first one treats all variables as a whole, while the second one utilizes the structural information by checking the individual local factors defined by the generative model and works better in practice. Finally, we present two important instances of Graphical-GAN, i.e. Gaussian Mixture GAN (GMGAN) and State Space GAN (SSGAN), which can successfully learn the discrete and temporal structures on visual datasets, respectively.

READ FULL TEXT

page 6

page 7

page 13

page 14

research
11/27/2018

Synthesizing Tabular Data using Generative Adversarial Networks

Generative adversarial networks (GANs) implicitly learn the probability ...
research
07/21/2020

Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective

Learning controllable and generalizable representation of multivariate d...
research
07/12/2023

Network Model with Application to Allergy Diseases

We propose a new graphical model to describe the comorbidity of allergic...
research
06/28/2021

Non-Exhaustive Learning Using Gaussian Mixture Generative Adversarial Networks

Supervised learning, while deployed in real-life scenarios, often encoun...
research
06/06/2019

Combining Generative and Discriminative Models for Hybrid Inference

A graphical model is a structured representation of the data generating ...
research
06/10/2018

Stochastic seismic waveform inversion using generative adversarial networks as a geological prior

We present an application of deep generative models in the context of pa...
research
03/05/2021

Contrastive Disentanglement in Generative Adversarial Networks

Disentanglement is defined as the problem of learninga representation th...

Please sign up or login with your details

Forgot password? Click here to reset