With a long history of traditional Graph Anomaly Detection (GAD) algorithms and recently
popular Graph Neural Networks (GNNs), it is still not clear (1) how they perform under a …

Graphs have a superior ability to represent relational data, such as chemical compounds,
proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as …

Graph anomaly detection (GAD), which aims to identify unusual graph instances (nodes,
edges, subgraphs, or graphs), has attracted increasing attention in recent years due to its …

Anomalous node detection in a static graph faces significant challenges due to the rarity of
anomalies and the substantial cost of labeling their deviant structure and attribute patterns …

Unsupervised graph anomaly detection is crucial for various practical applications as it aims
to identify anomalies in a graph that exhibit rare patterns deviating significantly from the …

Unsupervised GAD methods assume the lack of anomaly labels, ie, whether a node is
anomalous or not. One common observation we made from previous unsupervised methods …

A key component of many graph neural networks (GNNs) is the pooling operation, which
seeks to reduce the size of a graph while preserving important structural information …

Graph-level anomaly detection aims at capturing anomalous individual graphs in a graph
set. Due to its significance in various real-world application fields, eg, identifying rare …

Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous
nodes from graph-structured data in various domains such as medicine, social networks …

A large number of studies on Graph Outlier Detection (GOD) have emerged in recent years
due to its wide applications, in which Unsupervised Node Outlier Detection (UNOD) on …