Problem
Research questions and friction points this paper is trying to address.
Generalist Graph Anomaly Detection
Data Scarcity
Synthetic Data
Foundation Model
Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection?
🤖 AI Summary
This study addresses the bottleneck in general graph anomaly detection caused by the scarcity and high annotation cost of real-world anomalous data. To overcome this, it proposes the AG-FORGE framework for automatically synthesizing high-quality anomalous graphs, thereby surpassing the capacity limitations of existing methods. Furthermore, it introduces the TS-GGAD model, which achieves retraining-free generalizable detection capabilities through topology-semantics co-modeling and a large-scale curriculum learning strategy. This work validates the feasibility of synthetic data-driven training. Extensive experiments on 14 real-world datasets demonstrate that the proposed approach significantly outperforms state-of-the-art methods, proving that models trained on synthetic data can match or even exceed the performance achieved with real data.
📝 Abstract
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. 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. 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. 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. Extensive experiments on 14 real-world datasets demonstrate that TS-GGAD, trained on data generated by AG-FORGE, significantly outperforms state-of-the-art methods.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Generalist Graph Anomaly Detection
Synthetic Data Generation
Topology-Semantic Coordination
Curriculum Learning
Foundation Model
🔎 Similar Papers
No similar papers found.
