Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection

2026-05-26

AI Summary

This work addresses the limitations of existing graph anomaly detection methods, which often rely on fixed pipelines and weak supervision signals, thereby struggling to effectively integrate structural and contextual anomaly evidence under few-shot settings. To overcome these challenges, the authors propose SignGAD, a novel framework that introduces an agent-driven, self-designed workflow paradigm for graph anomaly detection. SignGAD dynamically generates task-conditioned detection pipelines by adaptively selecting from multiple graph encoders and composable detectors, and further incorporates a controlled final re-fitting strategy to enhance reliability in data-scarce scenarios. Extensive experiments on multiple real-world datasets demonstrate that SignGAD significantly outperforms current state-of-the-art methods, confirming its effectiveness and robustness.

Abstract

Graph anomaly detection aims to identify anomaly nodes in attributed graphs and plays an important role in real-world applications. However, existing graph anomaly detection methods still face two key challenges: 1) fixed pipelines, which restrict their adaptability across different graph tasks under limited supervision; 2) weak evidence, which prevents them from explicitly incorporating contextual and structural anomaly signals into the detection process. In this paper, we propose a novel framework, self-designing agentic workflows for few-shot graph anomaly detection (SignGAD). Specifically, we propose a novel paradigm that reformulates graph anomaly detection task from training a fixed anomaly detector to designing task-conditioned detection workflows. By constructing detection workflows, SignGAD selects suitable graph encodings and detector designs to exploit task-specific anomaly evidence. Meanwhile, we introduce a guarded final refit strategy to refine the selected workflow by calibrating refit acceptance, enhancing reliability under limited supervision. Extensive experiments conducted on several real-world datasets demonstrate that SignGAD achieves strong performance against state-of-the-art methods, highlighting its effectiveness on graph anomaly detection tasks.

Problem

• graph anomaly detection
• few-shot learning
• fixed pipelines
• anomaly evidence
• attributed graphs

Innovation

• self-designing workflows
• few-shot graph anomaly detection
• agentic detection
• task-conditioned workflow
• guarded refit