PDNS-Net: A Large Heterogeneous Graph Benchmark Dataset of Network Resolutions for Graph Learning

TL;DR

PDNS-Net is the largest public heterogeneous graph dataset for malicious domain classification, enabling more comprehensive evaluation of graph learning algorithms on large-scale, real-world data.

Contribution

This paper introduces PDNS-Net, a large-scale heterogeneous graph dataset for malicious domain classification, filling a gap in available datasets for heterogeneous graph learning.

Findings

PDNS-Net contains 447K nodes and 897K edges, significantly larger than existing datasets.

Preliminary evaluations show current graph neural networks need improvement on large heterogeneous graphs.

The dataset is publicly available for further research and benchmarking.

Abstract

In order to advance the state of the art in graph learning algorithms, it is necessary to construct large real-world datasets. While there are many benchmark datasets for homogeneous graphs, only a few of them are available for heterogeneous graphs. Furthermore, the latter graphs are small in size rendering them insufficient to understand how graph learning algorithms perform in terms of classification metrics and computational resource utilization. We introduce, PDNS-Net, the largest public heterogeneous graph dataset containing 447K nodes and 897K edges for the malicious domain classification task. Compared to the popular heterogeneous datasets IMDB and DBLP, PDNS-Net is 38 and 17 times bigger respectively. We provide a detailed analysis of PDNS-Net including the data collection methodology, heterogeneous graph construction, descriptive statistics and preliminary graph classification performance. The dataset is publicly available at https://github.com/qcri/PDNS-Net. Our preliminary evaluation of both popular homogeneous and heterogeneous graph neural networks on PDNS-Net reveals that further research is required to improve the performance of these models on large heterogeneous graphs.