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.

提出了一种名为Graphical Generative Adversarial Networks（Graphical-GAN）的模型，结合了贝叶斯网络和生成性对抗网络的能力来建模结构化数据。引入了一个结构化的识别模型来推断给定观测值的潜在变量的后验分布，并将期望传播（EP）算法广义化，以同时学习生成模型和识别模型。最后，提出了两个Graphical-GAN的重要实例，即高斯混合GAN（GMGAN）和状态空间GAN（SSGAN），可分别成功学习视觉数据集的离散和时间结构。

图形生成对抗网络