Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy

Graph autoencoders (Graph-AEs) learn representations of given graphs by aiming to accurately reconstruct them. A notable application of Graph-AEs is graph-level anomaly detection (GLAD), whose objective is to identify graphs with anomalous topological structures and/or node features compared to the...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Kim, Sunwoo, Lee, Soo Yong, Bu, Fanchen, Kang, Shinhwan, Kim, Kyungho, Yoo, Jaemin, Shin, Kijung
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Computer Science - Social and Information Networks
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!