Benchmarking Graph Neural Networks for Internet Routing Data

TL;DR

This paper introduces a benchmarking framework and dataset for applying graph neural networks to Internet routing data, enabling systematic evaluation of GNN models on Autonomous System graphs.

Contribution

It provides a new dataset, preprocessing pipeline, and benchmarking results for GNNs on Internet routing data, facilitating future research in this domain.

Findings

GNN models show varying efficiency on Internet data tasks.

Benchmark results establish baseline performance for future studies.

Preprocessing pipeline enables easy application of GNNs to heterogeneous AS data.

Abstract

The Internet is composed of networks, called Autonomous Systems (or, ASes), interconnected to each other, thus forming a large graph. While both the AS-graph is known and there is a multitude of data available for the ASes (i.e., node attributes), the research on applying graph machine learning (ML) methods on Internet data has not attracted a lot of attention. In this work, we provide a benchmarking framework aiming to facilitate research on Internet data using graph-ML and graph neural network (GNN) methods. Specifically, we compile a dataset with heterogeneous node/AS attributes by collecting data from multiple online sources, and preprocessing them so that they can be easily used as input in GNN architectures. Then, we create a framework/pipeline for applying GNNs on the compiled data. For a set of tasks, we perform a benchmarking of different GNN models (as well as, non-GNN ML models) to test their efficiency; our results can serve as a common baseline for future research and provide initial insights for the application of GNNs on Internet data.