A Generalizable Anomaly Detection Method in Dynamic Graphs
This addresses the lack of generalizability in deep learning-based anomaly detection for dynamic graphs, which is crucial in domains like social networks and cybersecurity, though it appears incremental as it builds on existing methods to improve specific challenges.
The paper tackles the problem of generalizability in anomaly detection for dynamic graphs by proposing GeneralDyG, which samples temporal ego-graphs and extracts structural and temporal features, achieving significant outperformance over state-of-the-art methods on four real-world datasets.
Anomaly detection aims to identify deviations from normal patterns within data. This task is particularly crucial in dynamic graphs, which are common in applications like social networks and cybersecurity, due to their evolving structures and complex relationships. Although recent deep learning-based methods have shown promising results in anomaly detection on dynamic graphs, they often lack of generalizability. In this study, we propose GeneralDyG, a method that samples temporal ego-graphs and sequentially extracts structural and temporal features to address the three key challenges in achieving generalizability: Data Diversity, Dynamic Feature Capture, and Computational Cost. Extensive experimental results demonstrate that our proposed GeneralDyG significantly outperforms state-of-the-art methods on four real-world datasets.