Poster
Graphical Generative Adversarial Networks
Chongxuan LI · Max Welling · Jun Zhu · Bo Zhang

Tue Dec 4th 10:45 AM -- 12:45 PM @ Room 210 #27
in Tue Poster Session A »

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 generalize the Expectation Propagation (EP) algorithm to learn the generative model and recognition model jointly. 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.

Keywords: Unsupervised Learning · Adversarial Networks · Generative Models

Author Information

Chongxuan LI (Tsinghua University)
Max Welling (University of Amsterdam / Qualcomm AI Research)
Jun Zhu (Tsinghua University)
Bo Zhang (Tsinghua University)

More from the Same Authors