Open Graph Benchmark

Benchmark datasets, data loaders and evaluators for graph machine learning

Getting Started

The Open Graph Benchmark (OGB) is a collection of benchmark datasets, data loaders, and evaluators for graph machine learning. Datasets cover a variety of graph machine learning tasks and real-world applications.

The OGB data loaders are fully compatible with popular graph deep learning frameworks, including Pytorch Geometric and DGL. They provide automatic dataset downloading, standardized dataset splits, and unified performance evaluation.

OGB is a community-driven initiative in active development. We expect the benchmark datasets to evolve. Subscribe to our google group to ask us questions and keep up to date with major changes to the datasets.

Jekyll logo

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.