snap-stanford/ogb
Open Graph Benchmark provides standardized datasets, data loaders, and evaluators for graph machine learning tasks.
Not currently ranked — collecting fresh signals.
star history
OGB is a collection of benchmark datasets covering node-level, link-level, and graph-level prediction tasks across diverse domains including scientific graphs, social networks, and knowledge graphs. It provides data loaders compatible with PyTorch Geometric and DGL, automatic dataset downloading, standardized splits, and unified performance evaluation for graph neural network models.
Frequently asked
- What is snap-stanford/ogb?
- Open Graph Benchmark provides standardized datasets, data loaders, and evaluators for graph machine learning tasks.
- Is ogb open source?
- Yes — snap-stanford/ogb is open source, released under the MIT license.
- What language is ogb written in?
- snap-stanford/ogb is primarily written in Python.
- How popular is ogb?
- snap-stanford/ogb has 2.1k stars on GitHub.
- Where can I find ogb?
- snap-stanford/ogb is on GitHub at https://github.com/snap-stanford/ogb.