What Does My GNN Really Capture? On Exploring Internal GNN Representations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

What Does My GNN Really Capture? On Exploring Internal GNN Representations

Résumé

GNNs are efficient for classifying graphs but their internal workings is opaque which limits their field of application. Existing methods for explaining GNN focus on disclosing the relationships between input graphs and the model's decision. In contrary, the method we propose isolates internal features, hidden in the network layers, which are automatically identified by the GNN to classify graphs. We show that this method makes it possible to know the parts of the input graphs used by GNN with much less bias than the SOTA methods and therefore to provide confidence in the decision process.
Fichier principal
Vignette du fichier
ijcai22.pdf (282.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03700710 , version 1 (21-06-2022)

Identifiants

  • HAL Id : hal-03700710 , version 1

Citer

Luca Veyrin-Forrer, Ataollah Kamal, Stefan Duffner, Marc Plantevit, Céline Robardet. What Does My GNN Really Capture? On Exploring Internal GNN Representations. International Joint Conference on Artificial Intelligence 2022, Jul 2022, Vienna, Austria. ⟨hal-03700710⟩
316 Consultations
323 Téléchargements

Partager

Gmail Facebook X LinkedIn More