graphdeeplearning/benchmarking-gnns

Repository for benchmarking graph neural networks (JMLR 2023)

50
/ 100
Established

This project helps researchers and developers evaluate the performance of different graph neural networks (GNNs) on various tasks. It takes standard graph datasets, such as molecular structures (ZINC, AQSOL) or theoretical graph properties (GraphTheoryProp, CYCLES), and outputs benchmark results, allowing for direct comparison of GNN architectures. This is for machine learning researchers, data scientists, and computational chemists who develop or apply GNNs.

2,650 stars. No commits in the last 6 months.

Use this if you need to rigorously compare different graph neural network models on diverse datasets to understand their strengths and weaknesses for specific applications.

Not ideal if you are looking for a pre-trained model for immediate inference or if you do not have experience working with machine learning benchmarks and model evaluation.

graph-analysis computational-chemistry machine-learning-research model-evaluation algorithm-benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

2,650

Forks

458

Language

Jupyter Notebook

License

MIT

Last pushed

Jun 22, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/graphdeeplearning/benchmarking-gnns"

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