GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps

Abstract

Detecting unusual patterns in graph data is a crucial task in data mining. However, existing methods face challenges in consistently achieving satisfactory performance and often lack interpretability, which hinders our understanding of anomaly detection decisions. In this paper, we propose a novel approach to graph anomaly detection that leverages the power of interpretability to enhance performance. Specifically, our method extracts an attention map derived from gradients of graph neural networks, which serves as a basis for scoring anomalies. Notably, our approach is flexible and can be used in various anomaly detection settings. In addition, we conduct theoretical analysis using synthetic data to validate our method and gain insights into its decision-making process. To demonstrate the effectiveness of our method, we extensively evaluate our approach against state-of-the-art graph anomaly detection techniques on real-world graph classification and wireless network datasets. The results consistently demonstrate the superior performance of our method compared to the baselines.

References in corpus (14)

• Semi-Supervised Classification with Graph Convolutional Networks
• Gaussian Error Linear Units (GELUs)
• Deep Learning for Anomaly Detection: A Review
• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• FANG: Leveraging Social Context for Fake News Detection Using Graph Representation
• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
• Parameterized Explainer for Graph Neural Network
• Generative Probabilistic Novelty Detection with Adversarial Autoencoders
• One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks
• Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs
• BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs
• Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
• Towards Self-Interpretable Graph-Level Anomaly Detection
• Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks