Communication Dans Un Congrès Année : 2024

Graph Convolutional Networks and Graph Attention Networks for Approximating Arguments Acceptability

Résumé

Various approaches have been proposed for providing efficient computational approaches for abstract argumentation. Among them, neural networks have permitted to solve various decision problems, notably related to arguments (credulous or skeptical) acceptability. In this work, we push further this study in various ways. First, relying on the state-of-the-art approach AFGCN, we show how we can improve the performances of the Graph Convolutional Networks (GCNs) regarding both runtime and accuracy. Then, we show that it is possible to improve even more the efficiency of the approach by modifying the architecture of the network, using Graph Attention Networks (GATs) instead.
Fichier principal
Vignette du fichier
FAIA-388-FAIA240307.pdf (274) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
licence

Dates et versions

hal-04948576 , version 1 (14-02-2025)

Licence

Identifiants

Citer

Paul Cibier, Jean-Guy Mailly. Graph Convolutional Networks and Graph Attention Networks for Approximating Arguments Acceptability. 10th International Conference on Computational Models of Argument (COMMA 2024), Sep 2024, Hagen, Germany. ⟨10.3233/FAIA240307⟩. ⟨hal-04948576⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More