mims-harvard/graphml-tutorials

Tutorials for Machine Learning on Graphs

48
/ 100
Emerging

This collection of tutorials helps data scientists and researchers understand and apply machine learning techniques to data that can be represented as graphs. You'll learn how to transform complex, interconnected datasets into a format suitable for graph neural networks and then use these networks to make predictions or uncover patterns. It's designed for anyone working with relational data, such as social networks, molecular structures, or interconnected systems.

230 stars. No commits in the last 6 months.

Use this if you need to analyze relationships and make predictions on data where connections between items are as important as the items themselves.

Not ideal if your data is primarily tabular or image-based, without significant underlying relational structures.

network-analysis drug-discovery social-network-analysis predictive-modeling relational-data
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

230

Forks

56

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 08, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mims-harvard/graphml-tutorials"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.