This repository is the official PyTorch implementation of the experiments in the following paper:

Keyulu Xu*, Weihua Hu*, Jure Leskovec, Stefanie Jegelka. How Powerful are Graph Neural Networks? ICLR 2019.

arXiv OpenReview

If you make use of the code/experiment or GIN algorithm in your work, please cite our paper (Bibtex below).

@inproceedings{
xu2018how,
title={How Powerful are Graph Neural Networks?},
author={Keyulu Xu and Weihua Hu and Jure Leskovec and Stefanie Jegelka},
booktitle={International Conference on Learning Representations},
year={2019},
url={https://openreview.net/forum?id=ryGs6iA5Km},
}

Install PyTorch following the instuctions on the [official website] (https://pytorch.org/). The code has been tested over PyTorch 0.4.1 and 1.0.0 versions.

Then install the other dependencies.

pip install -r requirements.txt

Unzip the dataset file

unzip dataset.zip

and run

python main.py

Default parameters are not the best performing-hyper-parameters. Hyper-parameters need to be specified through the commandline arguments. Please refer to our paper for the details of how we set the hyper-parameters.

Type

python main.py --help

to learn hyper-parameters to be specified.