A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models
It provides a systematic review for researchers and practitioners in graph-based applications like social media and e-commerce, but it is incremental as it synthesizes existing work without new results.
This paper surveys generalization in graph anomaly detection (GAD), addressing the problem of limited adaptability to real-world scenarios like shifting data distributions and scarce training samples, by reviewing methods such as transfer learning and foundation models to enhance detection performance across applications.
Graph anomaly detection (GAD) has attracted increasing attention in recent years for identifying malicious samples in a wide range of graph-based applications, such as social media and e-commerce. However, most GAD methods assume identical training and testing distributions and are tailored to specific tasks, resulting in limited adaptability to real-world scenarios such as shifting data distributions and scarce training samples in new applications. To address the limitations, recent work has focused on improving the generalization capability of GAD models through transfer learning that leverages knowledge from related domains to enhance detection performance, or developing "one-for-all" GAD foundation models that generalize across multiple applications. Since a systematic understanding of generalization in GAD is still lacking, in this paper, we provide a comprehensive review of generalization in GAD. We first trace the evolution of generalization in GAD and formalize the problem settings, which further leads to our systematic taxonomy. Rooted in this fine-grained taxonomy, an up-to-date and comprehensive review is conducted for the existing generalized GAD methods. Finally, we identify current open challenges and suggest future directions to inspire future research in this emerging field.