Open Graph Benchmark
Benchmark datasets, data loaders and evaluators for graph machine learning
The Open Graph Benchmark (OGB) is a collection of realistic, large-scale, and diverse benchmark datasets for machine learning on graphs.
OGB datasets are automatically downloaded, processed, and split using the OGB Data Loader. The model performance can be evaluated using the OGB Evaluator in a unified manner.
OGB is a community-driven initiative in active development. We expect the benchmark datasets to evolve. To keep up to date to major updates, subscribe to our google group here.
Realistic datasets
OGB provides a diverse set of challenging and realistic benchmark datasets that are of varying sizes and cover a variety graph machine learning tasks, including prediction of node, link, and graph properties.
Flexible data loaders
OGB fully automates dataset processing. The OGB data loaders automatically download and process graphs, provide graph objects that are fully compatible with Pytorch Geometric and DGL.
Unified evaluation
OGB provides standardized dataset splits and evaluators that allow for easy and reliable comparison of different models in a unified manner. OGB uses leaderboards to keep track of the state-of-the-art.
a