Skip to content
Code for Graphite iterative graph generation
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data Add source code May 31, 2018
README.md Update README.md Jun 7, 2019
__init__.py Add source code May 31, 2018
initializations.py Add source code May 31, 2018
input_data.py Add source code May 31, 2018
layers.py fix prefix in import statements Jul 9, 2018
model.py fix prefix in import statements Jul 9, 2018
optimizer.py Add source code May 31, 2018
preprocessing.py Add source code May 31, 2018
train.py Add source code May 31, 2018
train_siemens.py Add source code May 31, 2018

README.md

Graphite: Iterative Generative Modeling of Graphs

Source code for our paper "Graphite: Iterative Generative Modeling of Graphs".

If you find it helpful, please consider citing our paper.

@article{grover2018iterative,
  title={Graphite: Iterative Generative Modeling of Graphs},
  author={Grover, Aditya and Zweig, Aaron and Ermon, Stefano},
  journal={arXiv preprint arXiv:1803.10459},
  year={2018}
}

Requirements

  1. python 2.7
  2. Tensorflow
  3. Networkx 1.11

Training

python train.py --epochs 500 --model feedback --edge_dropout 0.5 --learning_rate 0.01 --autoregressive_scalar 0.5

This code was built on top of a graph autoencoder (GAE) implementation available here.

If you have any questions, feel free to contact adityag@cs.stanford.edu or azweig@cs.stanford.edu.

You can’t perform that action at this time.