GraphDS: Generating Realistic Graphs from Degree of Sequqnces

This repository is the official PyTorch implementation of GraphDS, a graph generative model using auto-regressive model.

Installation

Install PyTorch following the instuctions on the official website. The code has been tested over PyTorch 0.2.0 and 0.4.0 versions.

conda install pytorch torchvision cuda90 -c pytorch

Then install the other dependencies.

pip install -r requirements.txt

Generate input dataset

python .\main_dataset.py --config-path dataset1_config.toml --output-prefix dataset1

Training MS-VAE model

python .\main_dataset.py --config-path dataset1_config.toml --output-prefix dataset1

Training GraphES model

python .\main_dataset.py --config-path dataset1_config.toml --output-prefix dataset1