https://github.com/mims-harvard/graphml-tutorials

Tutorials for Machine Learning on Graphs
https://github.com/mims-harvard/graphml-tutorials

deep-learning embeddings graph-convolutional-networks graph-ml graph-neural-networks network-embeddings networks representation-learning tutorials

Last synced: 5 months ago
JSON representation

Tutorials for Machine Learning on Graphs

• Host: GitHub
• URL: https://github.com/mims-harvard/graphml-tutorials
• Owner: mims-harvard
• License: mit
• Created: 2020-06-26T15:00:38.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2021-07-08T09:24:51.000Z (over 4 years ago)
• Last Synced: 2024-03-26T02:22:12.094Z (almost 2 years ago)
• Topics: deep-learning, embeddings, graph-convolutional-networks, graph-ml, graph-neural-networks, network-embeddings, networks, representation-learning, tutorials
• Language: Jupyter Notebook
• Homepage:
• Size: 56.4 MB
• Stars: 195
• Watchers: 9
• Forks: 52
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Tutorials for Machine Learning on Graphs

![GitHub Workflow Status](https://img.shields.io/github/workflow/status/mims-harvard/graphml-tutorials/Run%20Dependency%20Test?logo=Python&logoColor=%23EE4C2C&style=flat)

## Contributors

- Payal Chandak (chandak@mit.edu)

- Haoxin Li (haoxin_li@hsph.harvard.edu)

- Min Jean Cho (min_jean_cho@brown.edu)

- Pavlin Policar (pavlin.policar@fri.uni-lj.si)

- Mert Erden (mert.erden@tufts.edu)

- Steffan Paul (steffanpaul@g.harvard.edu)

- Marinka Zitnik (marinka@hms.harvard.edu)

## Overview

Graph machine learning provides a powerful toolbox to learn representations from any arbitrary graph structure and use learned representations for a variety of downstream tasks. These tutorials aim to:

1. Introduce the concept of graph neural networks (GNNs).

2. Discuss the theoretical motivation behind different GNN architectures.

3. Provide implementations of these architectures.

4. Apply the architectures to key prediction problems on interconnected data in science and medicine.

5. Provide end-to-end real-world examples of graph machine learning.

![graph-ML](./graphML.png)

## Requirements

Recent versions of NumPy, PyTorch, PyTorch Geometric and Jupyter are required. 

## Installation

All the required packages can be installed using the following commands:

1. `git clone https://github.com/mims-harvard/graphml-tutorials.git`

2. `cd graphml-tutorials`

3. `chmod +x install.sh && ./install.sh`

4. `conda activate graphml_venv`

## Contributing

Pull requests are welcome.

## License

[MIT](https://choosealicense.com/licenses/mit/)