Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning

Abstract

Anomaly detection on attributed networks attracts considerable research interests due to wide applications of attributed networks in modeling a wide range of complex systems. Recently, the deep learning-based anomaly detection methods have shown promising results over shallow approaches, especially on networks with high-dimensional attributes and complex structures. However, existing approaches, which employ graph autoencoder as their backbone, do not fully exploit the rich information of the network, resulting in suboptimal performance. Furthermore, these methods do not directly target anomaly detection in their learning objective and fail to scale to large networks due to the full graph training mechanism. To overcome these limitations, in this paper, we present a novel contrastive self-supervised learning framework for anomaly detection on attributed networks. Our framework fully exploits the local information from network data by sampling a novel type of contrastive instance pair, which can capture the relationship between each node and its neighboring substructure in an unsupervised way. Meanwhile, a well-designed graph neural network-based contrastive learning model is proposed to learn informative embedding from high-dimensional attributes and local structure and measure the agreement of each instance pairs with its outputted scores. The multi-round predicted scores by the contrastive learning model are further used to evaluate the abnormality of each node with statistical estimation. In this way, the learning model is trained by a specific anomaly detection-aware target. Furthermore, since the input of the graph neural network module is batches of instance pairs instead of the full network, our framework can adapt to large networks flexibly. Experimental results show that our proposed framework outperforms the state-of-the-art baseline methods on all seven benchmark datasets.

arXiv comment15 pages, 5 figures, 6 tables. Published in IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

References in corpus (30)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• A Comprehensive Survey on Graph Neural Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Bootstrap your own latent: A new approach to self-supervised Learning
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Deep Learning for Anomaly Detection: A Review
• Spectral Networks and Locally Connected Networks on Graphs
• Learning deep representations by mutual information estimation and maximization
• Deep Convolutional Networks on Graph-Structured Data
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Self-supervised Learning: Generative or Contrastive
• Variational Graph Auto-Encoders
• Hierarchical Graph Representation Learning with Differentiable Pooling
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Attributed Social Network Embedding
• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• Exploring Simple Siamese Representation Learning
• Contrastive Multi-View Representation Learning on Graphs
• Learning Graph Embedding with Adversarial Training Methods
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Diffusion Improves Graph Learning
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Deep Weakly-supervised Anomaly Detection

Cited by in corpus (26)

• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• Graph Self-Supervised Learning: A Survey
• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
• Anomaly Detection in Dynamic Graphs via Transformer
• GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
• Unsupervised Outlier Detection using Memory and Contrastive Learning
• Graph Sequential Neural ODE Process for Link Prediction on Dynamic and Sparse Graphs
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
• Projective Ranking-based GNN Evasion Attacks
• GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs
• Hierarchically Fusing Long and Short-Term User Interests for Click-Through Rate Prediction in Product Search
• Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
• Class Label-aware Graph Anomaly Detection
• Multi-View Subgraph Neural Networks: Self-Supervised Learning with Scarce Labeled Data
• Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Voucher Abuse Detection with Prompt-based Fine-tuning on Graph Neural Networks
• UMGAD: Unsupervised Multiplex Graph Anomaly Detection
• EAGLE: Contrastive Learning for Efficient Graph Anomaly Detection
• How to Use Graph Data in the Wild to Help Graph Anomaly Detection?
• Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection
• Critical Review for One-class Classification: recent advances and the reality behind them