Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection?

Key points

• Sufficient data are essential for foundation model training, yet generalist GAD still faces a data shortage, as real-world anomalous graphs are scarce and costly to collect and annotate.1
• To fill this gap, we propose AG-FORGE, an Anomalous Graph generation Forge for automatic synthesis of anomalous graphs, exploring the feasibility of synthetic data-driven training for generalist GAD.1
• Empirically, we find that synthetic data can achieve performance comparable to real-world training, but fail to push the performance boundary further due to the limited capacity of existing methods.1
• To further unlock model capacity as training data scale up, we develop TS-GGAD, a Topology-Semantic coordinated Generalist GAD that captures complementary topological and semantic anomaly evidence, together with a curriculum learning strategy tailored to large-scale synthetic training.1

Sources (1)

• [1]Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection?
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 03:41 PM

  Generalist graph anomaly detection (GAD) aims to build a foundation model that detects anomalies on arbitrary unseen graphs without retraining or fine-tuning.

  Sufficient data are essential for foundation model training, yet generalist GAD still faces a data shortage, as real-world anomalous graphs are scarce and costly to collect and annotate.

Extractive summary: sentences quoted from the sources.