THUMNLab/awesome-graph-ood

Papers about out-of-distribution generalization on graphs.

36
/ 100
Emerging

This resource curates academic papers focused on methods for training machine learning models that work well with graph-structured data (like social networks or molecular structures), even when the data encountered in the real world is different from the training data. It categorizes research into approaches based on how data is handled, how models are designed, or what learning strategies are used. Data scientists and machine learning researchers who build and deploy models on graph data would use this to understand the latest techniques for ensuring their models are robust and generalize effectively.

168 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or data scientist working with graph neural networks and need to ensure your models perform reliably on new, unseen graph data that might have different characteristics from your training datasets.

Not ideal if you are looking for introductory material on graph neural networks or an off-the-shelf software tool for immediate use.

graph-machine-learning out-of-distribution-generalization robust-AI scientific-research ML-model-reliability
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

168

Forks

9

Language

License

MIT

Last pushed

Jun 05, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/THUMNLab/awesome-graph-ood"

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