Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity

TL;DR

This paper introduces a bi-directional curriculum learning approach for graph anomaly detection that considers both node homogeneity and heterogeneity, significantly enhancing detection performance across multiple models and datasets.

Contribution

It proposes a novel bi-directional curriculum learning strategy that addresses the limitations of existing methods by incorporating both homogeneity and heterogeneity in training.

Findings

BCL improves detection accuracy across ten models.

BCL is easily integrated into existing GAD methods.

Significant performance gains on seven datasets.

Abstract

Graph anomaly detection (GAD) aims to identify nodes from a graph that are significantly different from normal patterns. Most previous studies are model-driven, focusing on enhancing the detection effect by improving the model structure. However, these approaches often treat all nodes equally, neglecting the different contributions of various nodes to the training. Therefore, we introduce graph curriculum learning as a simple and effective plug-and-play module to optimize GAD methods. The existing graph curriculum learning mainly focuses on the homogeneity of graphs and treats nodes with high homogeneity as easy nodes. In fact, GAD models can handle not only graph homogeneity but also heterogeneity, which leads to the unsuitability of these existing methods. To address this problem, we propose an innovative Bi-directional Curriculum Learning strategy (BCL), which considers nodes with higher and lower similarity to neighbor nodes as simple nodes in the direction of focusing on homogeneity and focusing on heterogeneity, respectively, and prioritizes their training. Extensive experiments show that BCL can be quickly integrated into existing detection processes and significantly improves the performance of ten GAD anomaly detection models on seven commonly used datasets.