https://github.com/bstee615/gnn-tutorial

https://github.com/bstee615/gnn-tutorial

Science Score: 10.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
    Links to: arxiv.org
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: bstee615
  • License: cc0-1.0
  • Default Branch: master
  • Size: 84.3 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Fork of isolabs/gnn-tutorial
Created over 4 years ago · Last pushed over 4 years ago

https://github.com/bstee615/gnn-tutorial/blob/master/

# A Practical Guide to Graph Neural Networks

This repository contains the code for the extended examples in the paper ["A Practical Guide to Graph Neural Networks"](https://arxiv.org/abs/2010.05234).

If using the code here, or referencing the paper, please use the following bibtex citation entry for our preprint. 

```
@misc{ward2020practical,
      title={A Practical Guide to Graph Neural Networks}, 
      author={Isaac Ronald Ward and Jack Joyner and Casey Lickfold and Yulan Guo and Mohammed Bennamoun},
      year={2020},
      eprint={2010.05234},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}
```

## Folder structure

```
.
 html            # Exported .html files of the notebooks
 notebooks       # The .ipynb files of the example code
 .gitignore                     
 env.yml         # The conda environment dependencies file
 LICENSE
 README.md
```

## Running on your own computer

Although Jupyter notebooks (```notebooks/```) and exported HTML files (```html/```) have been included in this repository for ease of viewing and sharing, you may still want to clone this repository and run / modify the code yourself.

To do this, use a conda-based package manager and install dependencies from the file ```env.yml``` .yml file. Do this using the following command (or similar):

```
conda env create -f env.yml
```

Activate this environment and run the ```jupyter notebook``` command.

This code has been confirmed to work with Conda 4.10.3.

Owner

  • Name: Benjamin Steenhoek
  • Login: bstee615
  • Kind: user

3rd year PhD student @ ISU. Interests and research: deep learning, program analysis

GitHub Events

Total
Last Year