Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts

TL;DR

This paper introduces GAD-MoRE, a novel zero-shot graph anomaly detection framework that employs a mixture of Riemannian experts to better capture geometric differences across diverse anomaly patterns, significantly improving cross-domain detection.

Contribution

The paper proposes a mixture of Riemannian experts architecture with a multi-curvature feature alignment and dynamic routing for zero-shot graph anomaly detection, addressing geometric diversity issues.

Findings

GAD-MoRE outperforms state-of-the-art zero-shot GAD methods.

It surpasses few-shot fine-tuned models on unseen domains.

The approach effectively models diverse geometric anomaly patterns.

Abstract

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.