FGC-Comp: Adaptive Neighbor-Grouped Attribute Completion for Graph-based Anomaly Detection

TL;DR

FGC-Comp is a novel attribute completion method for graph anomaly detection that improves robustness against missing and adversarial attributes, enhancing prediction stability with minimal computational cost.

Contribution

It introduces a lightweight, classifier-agnostic attribute completion module that partitions neighbors, applies group-specific transforms, and fuses messages for better anomaly detection under incomplete data.

Findings

Effective on real-world fraud datasets

Enhances aggregation stability under missing attributes

Negligible additional computational overhead

Abstract

Graph-based Anomaly Detection models have gained widespread adoption in recent years, identifying suspicious nodes by aggregating neighborhood information. However, most existing studies overlook the pervasive issues of missing and adversarially obscured node attributes, which can undermine aggregation stability and prediction reliability. To mitigate this, we propose FGC-Comp, a lightweight, classifier-agnostic, and deployment-friendly attribute completion module-designed to enhance neighborhood aggregation under incomplete attributes. We partition each node's neighbors into three label-based groups, apply group-specific transforms to the labeled groups while a node-conditioned gate handles unknowns, fuse messages via residual connections, and train end-to-end with a binary classification objective to improve aggregation stability and prediction reliability under missing attributes. Experiments on two real-world fraud datasets validate the effectiveness of the approach with negligible computational overhead.