Effects of Locality and Rule Language on Explanations for Knowledge Graph Embeddings - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Effects of Locality and Rule Language on Explanations for Knowledge Graph Embeddings

Luis Galárraga
  • Function : Author
  • PersonId : 1121104

Abstract

Knowledge graphs (KGs) are key tools in many AI-related tasks such as reasoning or question answering. This has, in turn, propelled research in link prediction in KGs, the task of predicting missing relationships from the available knowledge. Solutions based on KG embeddings have shown promising results in this matter. On the downside, these approaches are usually unable to explain their predictions. While some works have proposed to compute post-hoc rule explanations for embedding-based link predictors, these efforts have mostly resorted to rules with unbounded atoms, e.g., bornIn(x,y)⇒residence(x,y), learned on a global scope, i.e., the entire KG. None of these works has considered the impact of rules with bounded atoms such as nationality(x,England)⇒speaks(x,English), or the impact of learning from regions of the KG, i.e., local scopes. We therefore study the effects of these factors on the quality of rule-based explanations for embedding-based link predictors. Our results suggest that more specific rules and local scopes can improve the accuracy of the explanations. Moreover, these rules can provide further insights about the inner-workings of KG embeddings for link prediction.
Fichier principal
Vignette du fichier
IDA_2023_paper_1620.pdf (502.89 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Licence : CC BY - Attribution

Dates and versions

hal-04132499 , version 1 (19-06-2023)

Licence

Attribution

Identifiers

Cite

Luis Galárraga. Effects of Locality and Rule Language on Explanations for Knowledge Graph Embeddings. IDA 2023 - Advances in Intelligent Data Analysis XXI, Apr 2023, Louvain-la-Neuve, Belgium. pp.143-155, ⟨10.1007/978-3-031-30047-9_12⟩. ⟨hal-04132499⟩
41 View
17 Download

Altmetric

Share

Gmail Facebook X LinkedIn More