divelab/GOOD

GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]

40
/ 100
Emerging

This project helps researchers and machine learning engineers evaluate how well graph-based AI models perform when encountering new, unexpected data patterns. It takes various graph datasets as input and outputs performance metrics for different models, indicating their generalization ability. It's designed for anyone working with graph neural networks who needs to assess model robustness to real-world data shifts.

207 stars. No commits in the last 6 months.

Use this if you need to benchmark the out-of-distribution generalization capabilities of graph deep learning algorithms across diverse graph datasets and data shifts.

Not ideal if you are looking for a pre-trained, production-ready graph model or a tool for general graph data analysis without a focus on out-of-distribution performance.

graph-machine-learning model-robustness scientific-research dataset-benchmarking AI-generalization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

207

Forks

22

Language

Python

License

GPL-3.0

Last pushed

Feb 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/divelab/GOOD"

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