A Generalizable Anomaly Detection Method in Dynamic Graphs

TL;DR

This paper introduces GeneralDyG, a novel anomaly detection method for dynamic graphs that effectively captures structural and temporal features, demonstrating superior performance across multiple real-world datasets.

Contribution

The paper presents GeneralDyG, a generalizable approach that samples ego-graphs and extracts features to improve anomaly detection in dynamic graphs, addressing key challenges of data diversity and computational efficiency.

Findings

Outperforms state-of-the-art methods on four datasets

Effectively captures structural and temporal features

Addresses challenges of data diversity and computational cost

Abstract

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.