UMGAD: Unsupervised Multiplex Graph Anomaly Detection

2024-11-19

arXiv.org

AI Summary

Unsupervised anomaly node detection on heterogeneous graphs with multiple interaction types remains challenging due to the difficulty of modeling complex relational structures and the reliance of existing methods on ground-truth labels for thresholding anomaly scores. To address this, we propose GMAE, a Graph Masked Autoencoder framework. Its key contributions are: (1) a novel dual-granularity graph augmentation strategy—operating at both attribute-level and subgraph-level—coupled with multi-relational feature fusion; (2) contrastive learning to enhance model sensitivity to anomalous structural patterns; and (3) a label-free, adaptive threshold selection mechanism. Evaluated on four benchmark heterogeneous graph datasets, GMAE achieves an average AUC of 89.72% (+13.48% over SOTA) and Macro-F1 of 78.35% (+11.68% over SOTA), demonstrating significant improvements over state-of-the-art approaches.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated 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

Graph anomaly detection (GAD) is a critical task in graph machine learning, with the primary objective of identifying anomalous nodes that deviate significantly from the majority. This task is widely applied in various real-world scenarios, including fraud detection and social network analysis. However, existing GAD methods still face two major challenges: (1) They are often limited to detecting anomalies in single-type interaction graphs and struggle with multiple interaction types in multiplex heterogeneous graphs. (2) In unsupervised scenarios, selecting appropriate anomaly score thresholds remains a significant challenge for accurate anomaly detection. To address the above challenges, we propose a novel Unsupervised Multiplex Graph Anomaly Detection method, named UMGAD. We first learn multi-relational correlations among nodes in multiplex heterogeneous graphs and capture anomaly information during node attribute and structure reconstruction through graph-masked autoencoder (GMAE). Then, to further extract abnormal information, we generate attribute-level and subgraph-level augmented-view graphs respectively, and perform attribute and structure reconstruction through GMAE. Finally, we learn to optimize node attributes and structural features through contrastive learning between original-view and augmented-view graphs to improve the model's ability to capture anomalies. Meanwhile, we also propose a new anomaly score threshold selection strategy, which allows the model to be independent of ground truth information in real unsupervised scenarios. Extensive experiments on four datasets show that our UMGAD significantly outperforms state-of-the-art methods, achieving average improvements of 13.48% in AUC and 11.68% in Macro-F1 across all datasets.

Problem

• Detects anomalies in multiplex heterogeneous graphs.
• Addresses unsupervised anomaly score threshold selection.
• Improves anomaly detection accuracy using contrastive learning.

Innovation

• Graph-masked autoencoder for node reconstruction
• Contrastive learning between original and augmented graphs
• Novel anomaly score threshold selection strategy