https://github.com/ermongroup/graphite
Code for Graphite iterative graph generation
https://github.com/ermongroup/graphite
Last synced: 5 months ago
JSON representation
Code for Graphite iterative graph generation
- Host: GitHub
- URL: https://github.com/ermongroup/graphite
- Owner: ermongroup
- Created: 2018-05-31T21:27:33.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-06-07T10:00:13.000Z (over 6 years ago)
- Last Synced: 2025-03-31T16:13:39.593Z (6 months ago)
- Language: Python
- Homepage:
- Size: 5.13 MB
- Stars: 59
- Watchers: 9
- Forks: 25
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Graphite: Iterative Generative Modeling of Graphs
Source code for our paper ["Graphite: Iterative Generative Modeling of Graphs"](https://arxiv.org/abs/1803.10459).
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](https://github.com/tkipf/gae).
If you have any questions, feel free to contact or .