NeighborDiv: Training-free Zero-shot Generalist Graph Anomaly Detection via Neighbor Diversity

TL;DR

NeighborDiv introduces a training-free, neighbor diversity-based approach for graph anomaly detection, achieving state-of-the-art results and robust cross-domain generalization without complex training pipelines.

Contribution

It proposes a novel neighbor diversity paradigm for GGAD, moving away from traditional neighbor consistency methods, enabling training-free, efficient, and stable anomaly detection.

Findings

Achieves 10.25% relative gain in AUC over baselines in SDIT.

Yields zero performance volatility across datasets.

Operates independently of training data dependency.

Abstract

Graph Anomaly Detection (GAD) is increasingly shifting to Generalist GAD (GGAD) for cross-domain "one-for-all" detection, but existing GGAD methods predominantly rely on the neighbor consistency principle, falling into the \textbf{Node-to-Neighbor Consistency Paradigm} for anomaly quantification. These methods suffer from complex training pipelines, heavy training data dependency, high computational costs, and unstable cross-domain generalization. To address these limitations, we propose NeighborDiv, a training-free generalist graph anomaly detection framework based on neighbor diversity. Departing from the dominant Node-to-Neighbor Consistency Paradigm, we shift the focus to the \textbf{Neighbor-to-Neighbor Diversity Paradigm}, and uncover that the internal structural dispersion of a node's neighbor set is a powerful, independently discriminative anomaly signal. We quantify neighbor diversity via the variance of inter-neighbor feature similarities, which captures how a node organizes its local graph environment, and operates independently of conventional node-to-neighbor consistency frameworks. Extensive experiments under two standard GGAD evaluation paradigms show NeighborDiv achieves state-of-the-art performance, with relative gains of 10.25% in average AUC and 17.78% in average AP over the second-best baseline under Single-Domain Independent Training (SDIT), and 6.89%/9.58% in AUC/AP under Unified Multi-Domain Training (UMDT), respectively. Notably, NeighborDiv yields zero performance volatility across all datasets, eliminating training-set dependency and establishing a lightweight and highly practical GGAD framework.