Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInE - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInE

Résumé

Knowledge graph embedding models (KGEMs) have gained considerable traction in recent years. These models learn a vector representation of knowledge graph entities and relations, a.k.a. knowledge graph embeddings (KGEs). Learning versatile KGEs is desirable as it makes them useful for a broad range of tasks. However, KGEMs are usually trained for a specific task, which makes their embeddings task-dependent. In parallel, the widespread assumption that KGEMs actually create a semantic representation of the underlying entities and relations (e.g., project similar entities closer than dissimilar ones) has been challenged. In this work, we design heuristics for generating protographs-small, modified versions of a KG that leverage RDF/S information. The learnt protograph-based embeddings are meant to encapsulate the semantics of a KG, and can be leveraged in learning KGEs that, in turn, also better capture semantics. Extensive experiments on various evaluation benchmarks demonstrate the soundness of this approach, which we call Modular and Agnostic SCHema-based Integration of protograph Embeddings (MASCHInE). In particular, MASCHInE helps produce more versatile KGEs that yield substantially better performance for entity clustering and node classification tasks. For link prediction, using MASCHinE substantially increases the number of semantically valid predictions with equivalent rank-based performance.
Fichier principal
Vignette du fichier
2306.03659.pdf (1.49 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04344873 , version 1 (14-12-2023)

Licence

Paternité

Identifiants

Citer

Nicolas Hubert, Heiko Paulheim, Pierre Monnin, Armelle Brun, Davy Monticolo. Schema First! Learn Versatile Knowledge Graph Embeddings by Capturing Semantics with MASCHInE. K-CAP 2023 - Knowledge Capture Conference 2023, Dec 2023, Pensacola, United States. pp.188-196, ⟨10.1145/3587259.3627550⟩. ⟨hal-04344873⟩
43 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More