Graphical Generative Adversarial Networks
Chongxuan Li, Max Welling, Jun Zhu, Bo Zhang
Abstract
Graphical GAN, 建模图像的结构信息(最近的好几篇工作都是围绕这个问题)
两种训练方法:global algorithm treats all variables as a wholel, ocal algorithm discriminates the individual local factors defined by the generative model separately.
两个Graphical GAN的具体实现,Gaussian Mixture GAN, State Space GAN
Introduction
Graphical GAN用Bayes网络表示变量间结构信息,还用深度隐式似然函数建模复杂数据,如图
左边表示GMGAN,右边表示SSGAN。白色圈表示显变量(可观测),灰色圈表示隐变量,单圈表示确定变量,双圈表示随机变量。 θ θ 表示全局参数。
implicit probabilistic models: deterministically transform Z to X and the likelihood can be intractable
prescribed probabilistic models: define the likelihood functions for X with an explicit specification
amortized inference: introduce a recognition model, which is a family of distributions of a simple form, to approximate the true posterior
mean-field assumption: all of the dependency structures among the latent variables are ignored and the approximate posterior could be factorized as