Explainable Representations for Relation Prediction in Knowledge Graphs

TL;DR

SEEK introduces explainable, multi-faceted representations for relation prediction in knowledge graphs, enhancing interpretability and performance in complex biomedical tasks by identifying shared semantic subgraphs.

Contribution

The paper presents SEEK, a novel method for generating explainable, subgraph-based representations that improve relation prediction accuracy and interpretability in knowledge graphs.

Findings

SEEK outperforms standard methods in relation prediction tasks.

It provides both sufficient and necessary explanations based on shared semantic aspects.

Achieves significant performance gains in biomedical relation prediction tasks.

Abstract

Knowledge graphs represent real-world entities and their relations in a semantically-rich structure supported by ontologies. Exploring this data with machine learning methods often relies on knowledge graph embeddings, which produce latent representations of entities that preserve structural and local graph neighbourhood properties, but sacrifice explainability. However, in tasks such as link or relation prediction, understanding which specific features better explain a relation is crucial to support complex or critical applications. We propose SEEK, a novel approach for explainable representations to support relation prediction in knowledge graphs. It is based on identifying relevant shared semantic aspects (i.e., subgraphs) between entities and learning representations for each subgraph, producing a multi-faceted and explainable representation. We evaluate SEEK on two real-world highly complex relation prediction tasks: protein-protein interaction prediction and gene-disease association prediction. Our extensive analysis using established benchmarks demonstrates that SEEK achieves significantly better performance than standard learning representation methods while identifying both sufficient and necessary explanations based on shared semantic aspects.