Temporal Graph Benchmark

Benchmark datasets for machine learning on temporal graphs, temporal knowledge graphs and temporal heterogeneous graphs.

Get Started

Temporal Graph Benchmark

TGB is a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation for machine learning on temporal graphs. TGB includes both dynamic link and node property prediction tasks and an automated pipeline from dataset downloading, dataloading, evaluation and submission to the TGB leaderboard. In TGB 2.0, we also included novel datasets for temporal knowledge graphs and temporal heterogeneous graphs. TGB is driven by community feedback and suggestions, if you would like to contribute a novel dataset or report any issues, please email us or visit our github.
Jekyll logo

Diverse Datasets

TGB provides diverse and realistic datasets, containing millions of nodes, edges and timestamps

Multiple Data Formats

TGB datasets are supported as numpy arrays, PyTorch tensors and PyG compatible TemporalData objects

Unified Evaluation

TGB provides dataset splits and evaluators for reproducible and standardized evaluation for temporal graphs, temporal knowledge graphs and temporal heterogeneous graphs.