Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts
About
Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to enable generalization to unseen graph datasets. However, existing zero-shot GAD methods largely ignore intrinsic geometric differences across diverse anomaly patterns, substantially limiting their cross-domain generalization. In this work, we reveal that anomaly detectability is highly dependent on the underlying geometric properties and that embedding graphs from different domains into a single static curvature space can distort the structural signatures of anomalies. To address the challenge that a single curvature space cannot capture geometry-dependent graph anomaly patterns, we propose GAD-MoRE, a novel framework for zero-shot Generalizable Graph Anomaly Detection with a Mixture of Riemannian Experts architecture. Specifically, to ensure that each anomaly pattern is modeled in the Riemannian space where it is most detectable, GAD-MoRE employs a set of specialized Riemannian expert networks, each operating in a distinct curvature space. To align raw node features with curvature-specific anomaly characteristics, we introduce an anomaly-aware multi-curvature feature alignment module that projects inputs into parallel Riemannian spaces, enabling the capture of diverse geometric characteristics. Finally, to facilitate better generalization beyond seen patterns, we design a memory-based dynamic router that adaptively assigns each input to the most compatible expert based on historical reconstruction performance on similar anomalies. Extensive experiments in the zero-shot setting demonstrate that GAD-MoRE significantly outperforms state-of-the-art generalist GAD baselines, and even surpasses strong competitors that are few-shot fine-tuned with labeled data from the target domain.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Graph Anomaly Detection | BlogCatalog | AUPRC0.3531 | 43 | |
| Graph Anomaly Detection | Cora | AUROC0.8639 | 40 | |
| Graph Anomaly Detection | AMAZON | AUROC76.9 | 35 | |
| Graph Anomaly Detection | Facebook (test) | -- | 32 | |
| Graph Anomaly Detection | Weibo (test) | -- | 32 | |
| Graph Anomaly Detection | AUROC0.7575 | 31 | ||
| Graph Anomaly Detection | ACM | AUROC0.8117 | 31 | |
| Graph Anomaly Detection | AUROC91.03 | 23 | ||
| Graph Anomaly Detection | Citeseer | AUROC90.28 | 23 | |
| Graph Anomaly Detection | Citeseer (test) | -- | 14 |