Communication Dans Un Congrès Année : 2025

A Comparative Analysis of Neuro-symbolic Methods for Link Prediction

Résumé

Link prediction on knowledge graphs is relevant to various applications, such as recommendation systems, question answering, and entity search. This task has been approached from different perspectives: symbolic methods leverage rule-based reasoning but struggle with scalability and noise, while knowledge graph embeddings (KGE) represent entities and relations in a continuous space, enabling scalability but often neglecting logical constraints from ontologies. Recently, neurosymbolic approaches have emerged to bridge this gap by integrating embedding-based learning with symbolic reasoning. This paper provides a structured review of state-of-the-art neurosymbolic methods for link prediction. Beyond a qualitative analysis, a key contribution of this work is a comprehensive experimental benchmarking, where we systematically compare these methods on the same datasets using the same metrics. This unified experimental setup allows for a fair assessment of their strengths and limitations, bringing elements of answers to following key questions: How accurate are these methods? How scalable are they? How beneficial are they for different levels of provided knowledge and to which extent are they robust to incorrect knowledge?

Fichier principal
Vignette du fichier
A_Comparative_Analysis_of_Nesy_methods_for_link_prediction.pdf (344.51 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04991391 , version 1 (17-03-2025)
hal-04991391 , version 2 (16-06-2025)
hal-04991391 , version 3 (25-08-2025)

Licence

Identifiants

  • HAL Id : hal-04991391 , version 3

Citer

Guillaume Olivier Delplanque, Luisa Sophie Werner, Nabil Layaïda, Pierre Genevès. A Comparative Analysis of Neuro-symbolic Methods for Link Prediction. NeSy 2025 - Proceedings of the 19th International Conference on Neurosymbolic Learning and Reasoning, Sep 2025, Santa Cruz, California, United States. ⟨hal-04991391v3⟩
289 Consultations
793 Téléchargements

Partager

  • More