GRAN

This is the official PyTorch implementation of Efficient Graph Generation with Graph Recurrent Attention Networks as described in the following NeurIPS 2019 paper:

@inproceedings{liao2019gran,
  title={Efficient Graph Generation with Graph Recurrent Attention Networks}, 
  author={Liao, Renjie and Li, Yujia and Song, Yang and Wang, Shenlong and Nash, Charlie and Hamilton, William L. and Duvenaud, David and Urtasun, Raquel and Zemel, Richard}, 
  booktitle={NeurIPS},
  year={2019}
}

Visualization

Generation of GRAN per step:

Overall generation process:

Dependencies

Python 3, PyTorch(1.2.0)

Other dependencies can be installed via

pip install -r requirements.txt

Run Demos

Train

To run the training of experiment X where X is one of {gran_grid, gran_DD, gran_DB, gran_lobster}:

python run_exp.py -c config/X.yaml

Note:

Please check the folder config for a full list of configuration yaml files.
Most hyperparameters in the configuration yaml file are self-explanatory.

Test

After training, you can specify the test_model field of the configuration yaml file with the path of your best model snapshot, e.g.,

test_model: exp/gran_grid/xxx/model_snapshot_best.pth
To run the test of experiments X:

python run_exp.py -c config/X.yaml -t

Note:

Please check the evaluation to set up.

Trained Models

You could use our trained model for comparisons. Please make sure you are using the same split of the dataset. Running the following script will download the trained model:

./download_model.sh

Sampled Graphs from GRAN

Proteins Graphs from Training Set:
Proteins Graphs Sampled from GRAN:

Cite

Please cite our paper if you use this code in your research work.

Questions/Bugs

Please submit a Github issue or contact [email protected] if you have any questions or find any bugs.

Project Name	Stars	Most Recent Commit	Open Issues	License	Language
Draw	501	5 years ago	9	apache-2.0	Python
TensorFlow Implementation of "DRAW: A Recurrent Neural Network For Image Generation"
Gran	363	a year ago	7	mit	C++
Efficient Graph Generation with Graph Recurrent Attention Networks, Deep Generative Model of Graphs, Graph Neural Networks, NeurIPS 2019
Ccm	187	5 years ago	6	apache-2.0	Python
This project is a tensorflow implement of our work, CCM.
Draw	131	8 years ago	4		Lua
Torch implementation of DRAW: A Recurrent Neural Network For Image Generation
Neural Question Generation	103	3 years ago	9	mit	Python
Pytorch implementation of Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks
Treegen	70	a year ago	23	mit	Python
A Tree-Based Transformer Architecture for Code Generation. (AAAI'20)
Tf Var Attention	55	3 years ago		mit	Python
Tensorflow Implementation of Variational Attention for Sequence to Sequence Models (COLING 2018)
Show_attend_and_tell_pytorch	51	4 years ago	5		Python
Pytorch implement Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Encoder Agnostic Adaptation	38	3 years ago	8	mit	Python
Encoder-Agnostic Adaptation for Conditional Language Generation
Recosa	36	3 years ago			Python
ReCoSa: Detecting the Relevant Contexts with Self-Attention for Multi-turn Dialogue Generation

Gran