Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphs

TL;DR

This paper introduces EL$^{2}$-DGAD, a semi-supervised framework for anomaly detection in dynamic graphs with very limited labels, utilizing a transformer encoder and contrastive learning to improve detection accuracy.

Contribution

The paper presents a novel dynamic graph anomaly detection method that effectively handles extremely limited labels using transformer-based encoding and contrastive learning.

Findings

Outperforms existing GAD methods on four datasets

Effective with very limited labeled data

Utilizes a transformer encoder for dynamic graph structure preservation

Abstract

Semi-supervised graph anomaly detection (GAD) has recently received increasing attention, which aims to distinguish anomalous patterns from graphs under the guidance of a moderate amount of labeled data and a large volume of unlabeled data. Although these proposed semi-supervised GAD methods have achieved great success, their superior performance will be seriously degraded when the provided labels are extremely limited due to some unpredictable factors. Besides, the existing methods primarily focus on anomaly detection in static graphs, and little effort was paid to consider the continuous evolution characteristic of graphs over time (dynamic graphs). To address these challenges, we propose a novel GAD framework (EL$^{2}$-DGAD) to tackle anomaly detection problem in dynamic graphs with extremely limited labels. Specifically, a transformer-based graph encoder model is designed to more effectively preserve evolving graph structures beyond the local neighborhood. Then, we incorporate an ego-context hypersphere classification loss to classify temporal interactions according to their structure and temporal neighborhoods while ensuring the normal samples are mapped compactly against anomalous data. Finally, the above loss is further augmented with an ego-context contrasting module which utilizes unlabeled data to enhance model generalization. Extensive experiments on four datasets and three label rates demonstrate the effectiveness of the proposed method in comparison to the existing GAD methods.