- Payal Chandak (payal.chandak@columbia.edu)
- Haoxin Li (haoxin_li@hsph.harvard.edu)
- Min Jean Cho (min_jean_cho@brown.edu)
- Pavlin Policar (pavlin.g.p@gmail.com)
- Marinka Zitnik (marinka@hms.harvard.edu)
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:
- Introduce the concept of graph neural networks (GNNs).
- Discuss the theoretical motivation behind different GNN architectures.
- Provide implementations of these architectures.
- Apply the architectures to key prediction problems on interconnected data in science and medicine.
- Provide end-to-end real-world examples of graph machine learning.
Recent versions of NumPy, PyTorch, PyTorch Geometric and Jupyter are required. All the required packages can be installed using the following command:
git clone https://github.com/mims-harvard/graphml-tutorials.gitcd graphml-tutorialsconda env create -f environment.ymlconda activate graphml_venv
Pull requests are welcome.