E-viri
Recenzirano
-
Shin, Yong-Min; Kim, Sun-Woo; Shin, Won-Yong
IEEE transactions on pattern analysis and machine intelligence, 2024-Mar-19, Letnik: PPJournal Article
Aside from graph neural networks (GNNs) attracting significant attention as a powerful framework revolutionizing graph representation learning, there has been an increasing demand for explaining GNN models. Although various explanation methods for GNNs have been developed, most studies have focused on instance-level explanations, which produce explanations tailored to a given graph instance. In our study, we propose Prototype-bAsed GNN-Explainer ( <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula> ) , a novel model-level GNN explanation method that explains what the underlying GNN model has learned for graph classification by discovering human-interpretable prototype graphs . Our method produces explanations for a given class , thus being capable of offering more concise and comprehensive explanations than those of instance-level explanations. First, <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula> selects embeddings of class-discriminative input graphs on the graph-level embedding space after clustering them. Then, <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula> discovers a common subgraph pattern by iteratively searching for high matching node tuples using node-level embeddings via a prototype scoring function, thereby yielding a prototype graph as our explanation. Using six graph classification datasets, we demonstrate that <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula> qualitatively and quantitatively outperforms the state-of-the-art model-level explanation method. We also carry out ystematic experimental studies by demonstrating the relationship between <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula> and instance-level explanation methods, the robustness of <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula> to input data scarce environments, and the computational efficiency of the proposed prototype scoring function in <inline-formula><tex-math>{\sf PAGE}</tex-math></inline-formula>.
![loading ... loading ...](themes/default/img/ajax-loading.gif)
Vnos na polico
Trajna povezava
- URL:
Faktor vpliva
Dostop do baze podatkov JCR je dovoljen samo uporabnikom iz Slovenije. Vaš trenutni IP-naslov ni na seznamu dovoljenih za dostop, zato je potrebna avtentikacija z ustreznim računom AAI.
Leto | Faktor vpliva | Izdaja | Kategorija | Razvrstitev | ||||
---|---|---|---|---|---|---|---|---|
JCR | SNIP | JCR | SNIP | JCR | SNIP | JCR | SNIP |
Baze podatkov, v katerih je revija indeksirana
Ime baze podatkov | Področje | Leto |
---|
Povezave do osebnih bibliografij avtorjev | Povezave do podatkov o raziskovalcih v sistemu SICRIS |
---|
Vir: Osebne bibliografije
in: SICRIS
To gradivo vam je dostopno v celotnem besedilu. Če kljub temu želite naročiti gradivo, kliknite gumb Nadaljuj.