From Few-Shot to Zero-Shot: Towards Generalist Graph Anomaly Detection

TL;DR

This paper introduces a novel generalist graph anomaly detection framework, ARC, capable of detecting anomalies across multiple datasets with minimal or no labeled data, significantly improving generalization and reducing retraining costs.

Contribution

The paper proposes ARC, a unified few-shot GAD method using in-context learning, and ARC_zero, a zero-shot variant for fully label-free anomaly detection on unseen datasets.

Findings

ARC achieves strong anomaly detection performance across diverse datasets.

ARC_zero enables effective zero-shot anomaly detection without labeled data.

Both methods demonstrate high efficiency and generalization in real-world scenarios.

Abstract

Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of "one-model-for-one-dataset", requiring dataset-specific training for each dataset to achieve optimal performance. However, this paradigm suffers from significant limitations, such as high computational and data costs, limited generalization and transferability to new datasets, and challenges in privacy-sensitive scenarios where access to full datasets or sufficient labels is restricted. To address these limitations, we propose a novel generalist GAD paradigm that aims to develop a unified model capable of detecting anomalies on multiple unseen datasets without extensive retraining/fine-tuning or dataset-specific customization. To this end, we propose ARC, a few-shot generalist GAD method that leverages in-context learning and requires only a few labeled normal samples at inference time. Specifically, ARC consists of three core modules: a feature Alignment module to unify and align features across datasets, a Residual GNN encoder to capture dataset-agnostic anomaly representations, and a cross-attentive in-Context learning module to score anomalies using few-shot normal context. Building on ARC, we further introduce ARC_zero for the zero-shot generalist GAD setting, which selects representative pseudo-normal nodes via a pseudo-context mechanism and thus enables fully label-free inference on unseen datasets. Extensive experiments on 17 real-world graph datasets demonstrate that both ARC and ARC_zero effectively detect anomalies, exhibit strong generalization ability, and perform efficiently under few-shot and zero-shot settings.