ARC: A Generalist Graph Anomaly Detector with In-Context Learning

TL;DR

ARC introduces a universal graph anomaly detection model that leverages in-context learning to identify anomalies across diverse datasets without retraining, significantly reducing costs and enhancing adaptability.

Contribution

This paper presents ARC, a novel generalist GAD approach using in-context learning to detect anomalies across multiple datasets without retraining or fine-tuning.

Findings

Outperforms existing methods on benchmark datasets.

Demonstrates high efficiency and generalizability.

Effective with few-shot normal samples at inference.

Abstract

Graph anomaly detection (GAD), which aims to identify abnormal nodes that differ from the majority within a graph, has garnered significant attention. However, current GAD methods necessitate training specific to each dataset, resulting in high training costs, substantial data requirements, and limited generalizability when being applied to new datasets and domains. To address these limitations, this paper proposes ARC, a generalist GAD approach that enables a ``one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly. Equipped with in-context learning, ARC can directly extract dataset-specific patterns from the target dataset using few-shot normal samples at the inference stage, without the need for retraining or fine-tuning on the target dataset. ARC comprises three components that are well-crafted for capturing universal graph anomaly patterns: 1) smoothness-based feature Alignment module that unifies the features of different datasets into a common and anomaly-sensitive space; 2) ego-neighbor Residual graph encoder that learns abnormality-related node embeddings; and 3) cross-attentive in-Context anomaly scoring module that predicts node abnormality by leveraging few-shot normal samples. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance, efficiency, and generalizability of ARC.