Bayesian GAN

by   Yunus Saatchi, et al.

Generative adversarial networks (GANs) can implicitly learn rich distributions over images, audio, and data which are hard to model with an explicit likelihood. We present a practical Bayesian formulation for unsupervised and semi-supervised learning with GANs. Within this framework, we use stochastic gradient Hamiltonian Monte Carlo to marginalize the weights of the generator and discriminator networks. The resulting approach is straightforward and obtains good performance without any standard interventions such as feature matching, or mini-batch discrimination. By exploring an expressive posterior over the parameters of the generator, the Bayesian GAN avoids mode-collapse, produces interpretable and diverse candidate samples, and provides state-of-the-art quantitative results for semi-supervised learning on benchmarks including SVHN, CelebA, and CIFAR-10, outperforming DCGAN, Wasserstein GANs, and DCGAN ensembles.


page 10

page 12

page 15

page 16


Good Semi-supervised Learning that Requires a Bad GAN

Semi-supervised learning methods based on generative adversarial network...

Bayesian Conditional Generative Adverserial Networks

Traditional GANs use a deterministic generator function (typically a neu...

Semi-Supervised Learning with GANs: Revisiting Manifold Regularization

GANS are powerful generative models that are able to model the manifold ...

Detecting Deceptive Reviews using Generative Adversarial Networks

In the past few years, consumer review sites have become the main target...

Teaching a GAN What Not to Learn

Generative adversarial networks (GANs) were originally envisioned as uns...

Linking generative semi-supervised learning and generative open-set recognition

This study investigates the relationship between semi-supervised learnin...

Semi-supervised Learning on Graphs with Generative Adversarial Nets

We investigate how generative adversarial nets (GANs) can help semi-supe...

Code Repositories


Tensorflow code for the Bayesian GAN ( (NIPS 2017)

view repo

Please sign up or login with your details

Forgot password? Click here to reset