Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning

2025-03-15

AI Summary

Existing graph neural network (GNN)-based anomaly detection methods rely heavily on the homophily assumption, rendering them ineffective at identifying anomalies that connect densely to normal nodes and overlooking diverse anomalous patterns embedded in local graph structures. To address unsupervised anomaly detection on heterogeneous graphs, we propose a Multi-Hypersphere Heterogeneous Graph Learning framework. Our method introduces an unsupervised neighborhood purification and enhancement encoding module to mitigate representation ambiguity, and jointly models global consistency and local context-aware anomaly discrimination. It integrates heterogeneous GNNs, neighborhood reconstruction, multi-hypersphere embedding space learning, and a local–global collaborative scoring strategy. Extensive experiments on ten real-world heterogeneous graph datasets demonstrate significant improvements over 14 state-of-the-art baselines. The source code is publicly available.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Graph Anomaly Detection (GAD) plays a vital role in various data mining applications such as e-commerce fraud prevention and malicious user detection. Recently, Graph Neural Network (GNN) based approach has demonstrated great effectiveness in GAD by first encoding graph data into low-dimensional representations and then identifying anomalies under the guidance of supervised or unsupervised signals. However, existing GNN-based approaches implicitly follow the homophily principle (i.e., the"like attracts like"phenomenon) and fail to learn discriminative embedding for anomalies that connect vast normal nodes. Moreover, such approaches identify anomalies in a unified global perspective but overlook diversified abnormal patterns conditioned on local graph context, leading to suboptimal performance. To overcome the aforementioned limitations, in this paper, we propose a Multi-hypersphere Heterophilic Graph Learning (MHetGL) framework for unsupervised GAD. Specifically, we first devise a Heterophilic Graph Encoding (HGE) module to learn distinguishable representations for potential anomalies by purifying and augmenting their neighborhood in a fully unsupervised manner. Then, we propose a Multi-Hypersphere Learning (MHL) module to enhance the detection capability for context-dependent anomalies by jointly incorporating critical patterns from both global and local perspectives. Extensive experiments on ten real-world datasets show that MHetGL outperforms 14 baselines. Our code is publicly available at https://github.com/KennyNH/MHetGL.

Problem

• Detects anomalies in graphs without labeled data
• Addresses limitations of homophily-based graph neural networks
• Improves anomaly detection by combining global and local perspectives

Innovation

• Unsupervised Heterophilic Graph Encoding for anomaly detection
• Multi-Hypersphere Learning for context-dependent anomaly patterns
• Combines global and local perspectives for enhanced detection