TGB Dataset Overview

The Temporal Graph Benchmark~(TGB) aims to provide datasets and evaluation protocols for realistic, reproducible, and robust evaluation for machine learning on temporal graphs.

Edge and Node-level tasks: We include both the dynamic link property prediction task and the dynamic node property prediction task

TKGs and THGs: We include the link property prediction task also for Temporal Knowledge Graphs and Temporal Heterogeneous Graphs.

Rich domains: TGB datasets come from interaction networks, rating networks, trasanction networks, traffic networks, social networks, trade networks, political networks, knowledge networks and software networks.

Diverse in scale: TGB datasets includes small, medium and large scale datasets

Leaderboard Submission

To submit to TGB datasets, please fill in the following google form and reach out to [email protected] if you have any questions. All results should be reported across 5 runs for both validation and test performance. Rules for the Leaderboard is found here.

Dataset splits

All datasets are split chronologically into the train, validation and test set with 70%, 15% and 15% of the edges respectively

Exploring datasets

You can plot temporal graph statistics or visualizations in our companion Python package: TGX. TGX is a Python library designed to analyze and visualize temporal graphs. All TGB datasets are directly supported in TGX, see our example tutorial here.

Contributing datasets

TGB welcomes community feedback and contributions, if you would like to contribute a datasets or raise an issue, please reach out by email.