TUDataset: A collection of benchmark datasets for learning with graphs
This addresses a bottleneck for researchers in graph learning by providing a comprehensive resource to facilitate advancements in the field.
The paper tackles the lack of standardized benchmark datasets and evaluation procedures for graph learning by introducing TUDataset, a collection of over 120 datasets for graph classification and regression, along with tools for reproducible experiments.
Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets and standardized evaluation procedures is lagging, consequently hindering advancements in this area. To address this, we introduce the TUDataset for graph classification and regression. The collection consists of over 120 datasets of varying sizes from a wide range of applications. We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools. Here, we give an overview of the datasets, standardized evaluation procedures, and provide baseline experiments. All datasets are available at www.graphlearning.io. The experiments are fully reproducible from the code available at www.github.com/chrsmrrs/tudataset.