/netgan_pytorch

Primary LanguageJupyter Notebook

NetGAN: Generating Graphs via Random Walks

Pytorch implementation of the method proposed in the paper: NetGAN: Generating Graphs via Random Walks
based on the tensorflow implementation: https://github.com/danielzuegner/netgan
The generator and the discriminator are defined in models.py. For better understanding the architectures of the models are shown as images below. The hyperparameters are defined respectively. main.py is a little demo version where a graph is created from a power grid.

How GANs work:

GAN

Generator model:

Generator

Discriminator model:

Discriminator