https://github.com/weihua916/powerful-gnns

How Powerful are Graph Neural Networks?
https://github.com/weihua916/powerful-gnns

deep-learning graph-convolutional-neural-networks graph-neural-networks

Last synced: 5 days ago
JSON representation

How Powerful are Graph Neural Networks?

• Host: GitHub
• URL: https://github.com/weihua916/powerful-gnns
• Owner: weihua916
• License: mit
• Created: 2018-12-26T18:37:44.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2021-07-01T16:45:36.000Z (over 3 years ago)
• Last Synced: 2024-11-19T18:40:01.313Z (24 days ago)
• Topics: deep-learning, graph-convolutional-neural-networks, graph-neural-networks
• Language: Python
• Size: 31 MB
• Stars: 1,187
• Watchers: 26
• Forks: 224
• Open Issues: 18
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-graph-classification - [Python Reference

README

        
# How Powerful are Graph Neural Networks?

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](https://arxiv.org/abs/1810.00826) [OpenReview](https://openreview.net/forum?id=ryGs6iA5Km) 

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},

}

```

## Installation

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

```

## Test run

Unzip the dataset file

```

unzip dataset.zip

```

and run

```

python main.py

```

The default parameters are not the best performing-hyper-parameters used to reproduce our results in the paper. 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. For instance, for the COLLAB and IMDB datasets, you need to add `--degree_as_tag` so that the node degrees are used for input node features.

To learn hyper-parameters to be specified, please type

```

python main.py --help

```

## Cross-validation strategy in the paper

The cross-validation in our paper only uses training and validation sets (no test set) due to small dataset size. Specifically, after obtaining 10 validation curves corresponding to 10 folds, we first took average of validation curves across the 10 folds (thus, we obtain an averaged validation curve), and then selected a single epoch that achieved the maximum averaged validation accuracy. Finally, the standard devision over the 10 folds was computed at the selected epoch.