AutoRDF2GML: Facilitating RDF Integration in Graph Machine Learning

TL;DR

AutoRDF2GML is a framework that automates the conversion of RDF data into graph machine learning features, including content and topology-based features, making RDF data more accessible for ML tasks and providing new benchmark datasets.

Contribution

The paper introduces AutoRDF2GML, the first automated framework for extracting content and topology features from RDF data for graph ML, along with new benchmark datasets.

Findings

Enables automated feature extraction from RDF data for ML tasks

Creates four new benchmark datasets from RDF knowledge graphs

Bridges the gap between Semantic Web and Graph ML communities

Abstract

In this paper, we introduce AutoRDF2GML, a framework designed to convert RDF data into data representations tailored for graph machine learning tasks. AutoRDF2GML enables, for the first time, the creation of both content-based features -- i.e., features based on RDF datatype properties -- and topology-based features -- i.e., features based on RDF object properties. Characterized by automated feature extraction, AutoRDF2GML makes it possible even for users less familiar with RDF and SPARQL to generate data representations ready for graph machine learning tasks, such as link prediction, node classification, and graph classification. Furthermore, we present four new benchmark datasets for graph machine learning, created from large RDF knowledge graphs using our framework. These datasets serve as valuable resources for evaluating graph machine learning approaches, such as graph neural networks. Overall, our framework effectively bridges the gap between the Graph Machine Learning and Semantic Web communities, paving the way for RDF-based machine learning applications.