TA-GGAD: Testing-time Adaptive Graph Model for Generalist Graph Anomaly Detection

TL;DR

This paper introduces TA-GGAD, a novel adaptive graph model that addresses cross-domain graph anomaly detection challenges by modeling feature mismatch patterns, achieving state-of-the-art accuracy across diverse real-world graphs.

Contribution

It proposes a new theoretical framework for the Anomaly Disassortativity issue and a graph foundation model that generalizes across multiple domains with a single training phase.

Findings

Achieves state-of-the-art detection accuracy on 14 real-world graphs.

Effectively addresses cross-domain generalization in graph anomaly detection.

Introduces the concept of Anomaly Disassortativity as a key factor in domain shift.

Abstract

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/.