Explainable Representations for Relation Prediction in Knowledge Graphs
It addresses the need for explainability in critical applications like biomedical relation prediction, though it is an incremental improvement over existing embedding methods.
The paper tackles the problem of explainable relation prediction in knowledge graphs by proposing SEEK, a method that identifies shared semantic subgraphs to create multi-faceted representations, achieving significantly better performance on protein-protein interaction and gene-disease association tasks.
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.