Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection

arXiv:2404.16366v1 Announce Type: new
Abstract: Unsupervised graph anomaly detection aims at identifying rare patterns that deviate from the majority in a graph without the aid of labels, which is important for a variety of real-world applications. Recent advances have utilized Graph Neural Networks (GNNs) to learn effective node representations by aggregating information from neighborhoods. This is motivated by the hypothesis that nodes in the graph tend to exhibit consistent behaviors with their neighborhoods. However, such consistency can be disrupted by …

abstract advances anomaly anomaly detection applications arxiv cs.ai cs.lg detection gnns graph graph neural networks labels learn networks neural networks node patterns type unsupervised world