Pré-Publication, Document De Travail Année : 2025

Graph Embeddings Meet Link Keys Discovery for Entity Matching

Ensiyeh Raoufi
  • Fonction : Auteur
  • PersonId : 1499690
Jérôme David
  • Fonction : Auteur
  • PersonId : 845592
Pierre Larmande
François Scharffe
Konstantin Todorov
Cassia Trojahn

Résumé

Entity Matching (EM) automates the discovery of identity links between entities within different Knowledge Graphs (KGs). Link keys are crucial for EM, serving as rules allowing to identify identity links across different KGs, possibly described using different ontologies. However, the approach for extracting link keys struggles to scale on large KGs. While embedding-based EM methods efficiently handle large KGs they lack explainability. This paper proposes a novel hybrid EM approach to guarantee the scalability link key extraction approach and improve the explainability of embeddingbased EM methods. First, embedding-based EM approaches are used to sample the KGs based on the identity links they generate, thereby reducing the search space to relevant sub-graphs for link key extraction. Second, rules (in the form of link keys) are extracted to explain the generation of identity links by the embedding-based methods. Experimental results demonstrate that the proposed approach allows link key extraction to scale on large KGs, preserving the quality of the extracted link keys. Additionally, it shows that link keys can improve the explainability of the identity links generated by embedding-methods, allowing for the regeneration of 77% of the identity links produced for a specific EM task, thereby providing an approximation of the reasons behind their generation.
Fichier principal
Vignette du fichier
Link_Keys_meet_Statistical_Approaches-6.pdf (592.22 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
licence

Dates et versions

hal-04920958 , version 1 (30-01-2025)

Licence

Identifiants

Citer

Chloé Khadija Jradeh, Ensiyeh Raoufi, Jérôme David, Pierre Larmande, François Scharffe, et al.. Graph Embeddings Meet Link Keys Discovery for Entity Matching. 2025. ⟨hal-04920958⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More