TUDatasets

A collection of benchmark datasets for graph classification and regression.

Learn more


This page contains collected benchmark datasets for the evaluation of graph kernels and graph neural networks. The datasets were collected by Christopher Morris, Nils M. Kriege, Franka Bause, Kristian Kersting, Petra Mutzel, and Marion Neumann with partial support of the German Science Foundation (DFG) within the Collaborative Research Center SFB 876 “Providing Information by Resource-Constrained Data Analysis”, project A6 “Resource-efficient Graph Mining”.

See also the accompanying paper (ICML 2020 workshop "Graph Representation Learning and Beyond"):

We also offer baseline implementations of standard graph kernels/graph neural network architecture, and standard evaluation procedures.

Jekyll logo