DyGADBench: A Comprehensive Benchmark for Anomaly Detection in Dynamic Graphs

Abstract

Dynamic graph anomaly detection (DGAD) is critical for a wide range of applications where abnormal events are rare, evolving, and tightly coupled with temporal context. Despite rapid progress in modeling dynamic graphs, the evaluation of DGAD methods remains fragmented, leaving the strengths, limitations, and trade-offs of state-of-the-art models poorly understood. We introduce DyGADBench, a comprehensive benchmark designed specifically for Dy namic G raph A nomaly D etection. It defines a diverse set of injected anomaly patterns spanning localized, global, and temporally persistent behaviors, reflecting a wide range of real-world scenarios; introduces a unifying taxonomy that organizes DGAD methods along core design axes, clarifying architectural and temporal modeling choices; and provides a unified and reproducible evaluation pipeline. We conduct an extensive empirical study of state-of-the-art DGAD models. Our findings reveal that detection difficulty increases consistently with anomaly complexity, from simple localized irregularities to coordinated and temporally persistent structures. We uncover a fundamental tension between architectural biases: methods emphasizing local structural information perform well on structure-dominated anomalies, while methods leveraging global temporal context excel on long-range anomalies, yet no approach reliably handles both. Moreover, scalability emerges as a critical bottleneck, with many high-performing methods incurring prohibitive computational or memory costs on large dynamic graphs. Together, these findings provide systematic insights into the interplay between anomaly characteristics, model design, and scalability, and point toward key directions for future research in dynamic graph anomaly detection. DyGADBench is publicly available at: https://github.com/Dastamn/dgadb.