evoKGsim+: A Framework for Tailoring Knowledge Graph-Based Similarity for Supervised Learning

Sousa, Rita; Silva, Sara; Pesquita, Cátia

doi:10.1007/978-3-030-80418-3_26

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a fundamentally distinct task from link prediction, where the training set relations are part of the KG. To tackle this relation prediction task, common approaches typically employ three steps: (1) generate embeddings for each entity in the KG; (2) aggregate the embeddings of each entity in a pair into a single representation; (3) use these aggregated representations as input to a supervised learning algorithm to learn a relation prediction model (Sousa, Silva, and Pesquita 2021;Celebi et al 2019). This generates non-explainable predictions since KG embeddings are, of course, non-explainable, as each dimension does not represent any particular meaning, which poses a serious limitation to the use of KG embeddings in a scientific setting.…”

Section: Problem Overviewmentioning

confidence: 99%

Explainable Representations for Relation Prediction in Knowledge Graphs

Sousa

Silva

Pesquita

2023

Proceedings of the Twentieth International Conference on Principles of Knowledge Representation and Reasoning

View full text Add to dashboard Cite

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 comparable or even superior performance to standard learning representation methods while identifying both sufficient and necessary explanations based on shared semantic aspects.

show abstract

Section: Problem Overviewmentioning

confidence: 99%