TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection
It addresses the need for effective identification of anomalous nodes like fake news and malicious transactions across multiple domains, which is crucial for maintaining the health of graph data ecosystems, representing a novel theoretical and practical advancement rather than an incremental improvement.
The paper tackles the problem of domain shift in cross-domain graph anomaly detection by identifying and modeling the Anomaly Disassortativity issue, and introduces a graph foundation model that achieves state-of-the-art detection accuracy across fourteen diverse real-world graphs with a single training phase.
A significant number of anomalous nodes in the real world, such as fake news, noncompliant users, malicious transactions, and malicious posts, severely compromises the health of the graph data ecosystem and urgently requires effective identification and processing. With anomalies that span multiple data domains yet exhibit vast differences in features, cross-domain detection models face severe domain shift issues, which limit their generalizability across all domains. This study identifies and quantitatively analyzes a specific feature mismatch pattern exhibited by domain shift in graph anomaly detection, which we define as the \emph{Anomaly Disassortativity} issue ($\mathcal{AD}$). Based on the modeling of the issue $\mathcal{AD}$, we introduce a novel graph foundation model for anomaly detection. It achieves cross-domain generalization in different graphs, requiring only a single training phase to perform effectively across diverse domains. The experimental findings, based on fourteen diverse real-world graphs, confirm a breakthrough in the model's cross-domain adaptation, achieving a pioneering state-of-the-art (SOTA) level in terms of detection accuracy. In summary, the proposed theory of $\mathcal{AD}$ provides a novel theoretical perspective and a practical route for future research in generalist graph anomaly detection (GGAD). The code is available at https://anonymous.4open.science/r/Anonymization-TA-GGAD/.