On the Replicability of Knowledge Enhanced Neural Networks in a Graph Neural Network Framework - Laboratoire d'Informatique de Grenoble Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

On the Replicability of Knowledge Enhanced Neural Networks in a Graph Neural Network Framework

Nabil Layaïda
Pierre Genèves

Résumé

In order to extend Knowledge Enhanced Neural Networks, we investigate the replicability of the approach and present a re-implementation of Knowledge Enhanced Neural Networks based on a Graph Neural Network framework (PyTorch Geometric). Knowledge Enhanced Neural Networks integrate prior knowledge in the form of logical formulas into an Artificial Neural Network by adding additional Knowledge Enhancement layers. The obtained results show that the model outperforms pure neural models as well as Neural-Symbolic models. Our long term goal is to be able to address more complex and large-scale knowledge graphs and to benefit from the wide range of functionalities available in PyTorch Geometric. To ensure that our implementation produces the same results, we replicate the original transductive experiments and explain the various challenges and the steps that we went through to reach that goal.
Fichier principal
Vignette du fichier
nesy22hal.pdf (163.07 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04035305 , version 1 (09-06-2022)
hal-04035305 , version 2 (17-03-2023)
hal-04035305 , version 3 (20-03-2023)
hal-04035305 , version 4 (13-12-2023)

Identifiants

  • HAL Id : hal-04035305 , version 1

Citer

Luisa Werner, Nabil Layaïda, Pierre Genèves. On the Replicability of Knowledge Enhanced Neural Networks in a Graph Neural Network Framework. 2022. ⟨hal-04035305v1⟩
381 Consultations
237 Téléchargements

Partager

Gmail Facebook X LinkedIn More