The Role of Graph Topology in the Performance of Biomedical Knowledge Graph Completion Models

TL;DR

This paper investigates how the topology of biomedical knowledge graphs influences the performance of completion models, providing insights and tools to improve their practical utility in biomedical research tasks.

Contribution

It offers a comprehensive analysis of biomedical knowledge graph topologies and their impact on model accuracy, along with new tools and datasets for further research.

Findings

Topological properties correlate with model performance.

Certain graph structures enhance knowledge graph completion accuracy.

Community resources are provided for ongoing research.

Abstract

Knowledge Graph Completion has been increasingly adopted as a useful method for helping address several tasks in biomedical research, such as drug repurposing or drug-target identification. To that end, a variety of datasets and Knowledge Graph Embedding models have been proposed over the years. However, little is known about the properties that render a dataset, and associated modelling choices, useful for a given task. Moreover, even though theoretical properties of Knowledge Graph Embedding models are well understood, their practical utility in this field remains controversial. In this work, we conduct a comprehensive investigation into the topological properties of publicly available biomedical Knowledge Graphs and establish links to the accuracy observed in real-world tasks. By releasing all model predictions and a new suite of analysis tools we invite the community to build upon our work and continue improving the understanding of these crucial applications.