Tutorials for Machine Learning on Graphs

Contributors

• Payal Chandak ([email protected])
• Haoxin Li ([email protected])
• Min Jean Cho ([email protected])
• Pavlin Policar ([email protected])
• Mert Erden ([email protected])
• Steffan Paul ([email protected])
• Marinka Zitnik ([email protected])

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.

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