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

2025-01-25

AI Summary

To address the severe performance degradation of semi-supervised anomaly detection in dynamic graphs under extremely scarce labels (0.1%–1%), this paper proposes a novel framework integrating temporal modeling and weakly supervised optimization. Our method introduces: (1) a Transformer-based dynamic graph encoder that explicitly models the temporal evolution of node ego-contexts; (2) a novel ego-context hypersphere classification loss, the first of its kind, enabling robust discriminative learning under ultra-low labeling rates; and (3) an unsupervised ego-context contrastive learning module to enhance structural consistency in representations. Evaluated on four standard dynamic graph benchmarks, our approach achieves an average 8.3% improvement in AUC over state-of-the-art methods—marking the first demonstration of stable, high-performance dynamic graph anomaly detection under extremely limited supervision.

Technology Category

• Machine Learning: Semi-Supervised Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Dynamic Graphs
• Anomaly Detection
• Sparse Information

Innovation

• EL2-DGAD
• Transformer Model
• Contrastive Learning