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

• URL: http://arxiv.org/abs/2311.06153v2
• Date: Wed, 26 Jun 2024 20:24:08 GMT
• Title: GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps
• Authors: Yifei Yang, Peng Wang, Xiaofan He, Dongmian Zou,
• Abstract summary: We propose a novel approach to graph anomaly detection that leverages the power of interpretability to enhance performance. Our method extracts an attention map derived from gradients of graph neural networks, which serves as a basis for scoring anomalies. We extensively evaluate our approach against state-of-the-art graph anomaly detection techniques on real-world graph classification and wireless network datasets.
• Score: 26.011499804523808
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Anomaly Detection in Graph Structured Data: A Survey [0.46040036610482665]
  We discuss a comprehensive overview of anomaly detection techniques on graph data. We present a new taxonomy that categorizes the different state-of-the-art anomaly detection methods.
  arXiv  Detail & Related papers  (2024-05-10T01:30:25Z)
• Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks [9.708651460086916]
  In this paper, we revisit datasets and approaches for unsupervised node-level graph anomaly detection tasks. Firstly, we introduce outlier injection methods that create more diverse and graph-based anomalies in graph datasets. Secondly, we compare methods employing message passing against those without, uncovering the unexpected decline in performance.
  arXiv  Detail & Related papers  (2024-03-06T19:42:34Z)
• Towards Self-Interpretable Graph-Level Anomaly Detection [73.1152604947837]
  Graph-level anomaly detection (GLAD) aims to identify graphs that exhibit notable dissimilarity compared to the majority in a collection. We propose a Self-Interpretable Graph aNomaly dETection model ( SIGNET) that detects anomalous graphs as well as generates informative explanations simultaneously.
  arXiv  Detail & Related papers  (2023-10-25T10:10:07Z)
• GraphCloak: Safeguarding Task-specific Knowledge within Graph-structured Data from Unauthorized Exploitation [61.80017550099027]
  Graph Neural Networks (GNNs) are increasingly prevalent in a variety of fields. Growing concerns have emerged regarding the unauthorized utilization of personal data. Recent studies have shown that imperceptible poisoning attacks are an effective method of protecting image data from such misuse. This paper introduces GraphCloak to safeguard against the unauthorized usage of graph data.
  arXiv  Detail & Related papers  (2023-10-11T00:50:55Z)
• A Complex Network based Graph Embedding Method for Link Prediction [0.0]
  We present a novel graph embedding approach based on the popularity-similarity and local attraction paradigms. We show, using extensive experimental analysis, that the proposed method outperforms state-of-the-art graph embedding algorithms.
  arXiv  Detail & Related papers  (2022-09-11T14:46:38Z)
• Benchmarking Node Outlier Detection on Graphs [90.29966986023403]
  Graph outlier detection is an emerging but crucial machine learning task with numerous applications. We present the first comprehensive unsupervised node outlier detection benchmark for graphs called UNOD.
  arXiv  Detail & Related papers  (2022-06-21T01:46:38Z)
• Raising the Bar in Graph-level Anomaly Detection [33.737428672049255]
  We present a new deep learning approach that significantly improves existing one-class approaches. Our method achieves an average performance improvement of 11.8% AUC compared to the best existing approach.
  arXiv  Detail & Related papers  (2022-05-27T09:17:57Z)
• Optimal Propagation for Graph Neural Networks [51.08426265813481]
  We propose a bi-level optimization approach for learning the optimal graph structure. We also explore a low-rank approximation model for further reducing the time complexity.
  arXiv  Detail & Related papers  (2022-05-06T03:37:00Z)
• From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach [49.439021563395976]
  Anomaly detection from graph data is an important data mining task in many applications such as social networks, finance, and e-commerce. We propose a novel framework, graph ANomaly dEtection framework with Multi-scale cONtrastive lEarning (ANEMONE in short) By using a graph neural network as a backbone to encode the information from multiple graph scales (views), we learn better representation for nodes in a graph.
  arXiv  Detail & Related papers  (2022-02-11T09:45:11Z)
• Bayesian Graph Contrastive Learning [55.36652660268726]
  We propose a novel perspective of graph contrastive learning methods showing random augmentations leads to encoders. Our proposed method represents each node by a distribution in the latent space in contrast to existing techniques which embed each node to a deterministic vector. We show a considerable improvement in performance compared to existing state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-12-15T01:45:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.