TUDataset: A collection of benchmark datasets for learning with graphs

TL;DR

The paper introduces TUDataset, a comprehensive collection of over 120 benchmark datasets for graph classification and regression, along with standardized evaluation tools to facilitate progress in graph neural network research.

Contribution

It provides a large, diverse dataset collection, standardized evaluation procedures, and baseline implementations to advance learning with graph data.

Findings

Over 120 datasets covering various applications

Standardized evaluation procedures established

Baseline results for graph neural networks provided

Abstract

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.