Improving the Quality of Rule-Based GNN Explanations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Improving the Quality of Rule-Based GNN Explanations

Résumé

Recent works have proposed to explain GNNs using activation rules. Activation rules allow to capture specific configurations in the embedding space of a given layer that is discriminant for the GNN decision. These rules also catch hidden features of input graphs. This requires to associate these rules to representative graphs. In this paper, we propose on the one hand an analysis of heuristic-based algorithms to extract the activation rules, and on the other hand the use of transport-based optimal graph distances to associate each rule with the most specific graph that triggers them.
Fichier principal
Vignette du fichier
kamal.22.xkdd.pdf (698.44 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04580342 , version 1 (19-05-2024)

Identifiants

Citer

Ataollah Kamal, Elouan Vincent, Marc Plantevit, Céline Robardet. Improving the Quality of Rule-Based GNN Explanations. Workshop on eXplainable Knowledge Discovery in Data Mining. Machine Learning and Principles and Practice of Knowledge Discovery in Databases - International Workshops of ECML PKDD 2022, Grenoble, France, September 19-23, 2022, Proceedings, Part I, Sep 2022, Grenoble, France. pp.467--482, ⟨10.1007/978-3-031-23618-1\_31⟩. ⟨hal-04580342⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More