Flex-GAD : Flexible Graph Anomaly Detection

TL;DR

Flex-GAD is an unsupervised graph anomaly detection framework that combines community-aware structural encoding with attribute encoding, using self-attention to adaptively fuse representations, achieving higher accuracy and faster training on real-world attributed graphs.

Contribution

It introduces a novel community-based GCN encoder and a self-attention fusion module, enhancing anomaly detection accuracy and efficiency over existing methods.

Findings

Achieves 7.98% higher AUC than previous best GAD-NR.

Runs 102x faster per epoch than Anomaly DAE.

Demonstrates effectiveness across diverse real-world attributed graphs.

Abstract

Detecting anomalous nodes in attributed networks, where each node is associated with both structural connections and descriptive attributes, is essential for identifying fraud, misinformation, and suspicious behavior in domains such as social networks, academic citation graphs, and e-commerce platforms. We propose Flex-GAD, a novel unsupervised framework for graph anomaly detection at the node level. Flex-GAD integrates two encoders to capture complementary aspects of graph data. The framework incorporates a novel community-based GCN encoder to model intra-community and inter-community information into node embeddings, thereby ensuring structural consistency, along with a standard attribute encoder. These diverse representations are fused using a self-attention-based representation fusion module, which enables adaptive weighting and effective integration of the encoded information. This fusion mechanism allows automatic emphasis of the most relevant node representation across different encoders. We evaluate Flex-GAD on seven real-world attributed graphs with varying sizes, node degrees, and attribute homogeneity. Flex-GAD achieves an average AUC improvement of 7.98% over the previously best-performing method, GAD-NR, demonstrating its effectiveness and flexibility across diverse graph structures. Moreover, it significantly reduces training time, running 102x faster per epoch than Anomaly DAE and 3x faster per epoch than GAD-NR on average across seven benchmark datasets.