DDGAD: Trajectory Dynamics for Diffusion-Based Graph Anomaly Detection

2026-05-25

AI Summary

This work addresses the issue of anomaly contamination propagation caused by message passing in graph anomaly detection and proposes a diffusion-based detection framework. The method distinguishes node behaviors through trajectory dynamics: normal nodes exhibit stable trajectories under the coupling of diffusion regularization and reliability-aware neighborhood consensus, whereas anomalous nodes display unstable dynamics due to directional conflict between global manifold priors and local contaminated signals. A novel distributed reliability-aware consensus mechanism is introduced, which integrates three complementary anomaly signals—neighbor inconsistency, reliability-weighted influence, and dynamic conflict energy—and provides theoretical guarantees for the trajectory stability of normal nodes. Extensive experiments on five real-world graph datasets demonstrate that the proposed approach significantly outperforms existing state-of-the-art methods.

Abstract

Graph anomaly detection (GAD) aims to identify nodes or substructures whose behavior or attributes deviate significantly from the overall pattern in graph-structured data, with critical applications in financial risk control, social network analysis, and cybersecurity. However, existing GCN-based methods suffer from the fundamental problem of contamination propagation, where anomalous nodes pollute the representations of their neighbors through message passing, leading to degraded detection performance. In this paper, we propose DDGAD, a novel diffusion-based graph anomaly detection framework that leverages trajectory dynamics to distinguish normal and anomalous nodes. Our key insight is that normal nodes exhibit consistent and stable representation trajectories under the coupled effects of diffusion regularization and reliability-aware neighborhood consensus, while anomalous nodes exhibit unstable and conflicting dynamics due to the directional disagreement between the global manifold prior and locally contaminated message passing. To mitigate contamination propagation, we introduce a distributed reliability-aware consensus refinement mechanism and define three complementary anomaly signals: neighbor inconsistency, reliability weight, and dynamical conflict energy. We further provide a preliminary theoretical analysis on normal node stability under the coupled dynamics. These signals collectively characterize anomalous behaviors from the perspectives of local inconsistency, consensus reliability, and dynamical instability. Extensive experiments on five real-world datasets demonstrate the effectiveness of the proposed framework.

Problem

• graph anomaly detection
• contamination propagation
• message passing
• anomalous nodes
• representation pollution

Innovation

• trajectory dynamics
• diffusion-based graph anomaly detection
• contamination propagation
• reliability-aware consensus
• dynamical conflict energy