snap-stanford/ogb
Benchmark datasets, data loaders, and evaluators for graph machine learning
This provides ready-to-use graph datasets, data loaders, and standardized evaluation tools for machine learning tasks on graphs. You input raw graph data, and it outputs pre-processed, split datasets compatible with popular graph deep learning frameworks, along with consistent performance metrics. It's ideal for machine learning researchers and practitioners working with graph-structured data across various domains.
2,076 stars. Used by 3 other packages. No commits in the last 6 months. Available on PyPI.
Use this if you need pre-configured, diverse graph datasets and a consistent way to evaluate your graph machine learning models without dealing with manual data preparation and splitting.
Not ideal if you are a non-developer or if your primary focus is not on developing or benchmarking graph machine learning models.
Stars
2,076
Forks
406
Language
Python
License
MIT
Category
Last pushed
May 06, 2025
Commits (30d)
0
Dependencies
8
Reverse dependents
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/snap-stanford/ogb"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pyg-team/pytorch_geometric
Graph Neural Network Library for PyTorch
a-r-j/graphein
Protein Graph Library
raamana/graynet
Subject-wise networks from structural MRI, both vertex- and voxel-wise features (thickness, GM...
pykale/pykale
Knowledge-Aware machine LEarning (KALE): accessible machine learning from multiple sources for...
dmlc/dgl
Python package built to ease deep learning on graph, on top of existing DL frameworks.