Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges

  title={Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges},
  author={Hwan Kim and Byung Suk Lee and Won-Yong Shin and Sungsu Lim},
  journal={IEEE Access},
Graphs are used widely to model complex systems, and detecting anomalies in a graph is an important task in the analysis of complex systems. Graph anomalies are patterns in a graph that do not conform to normal patterns expected of the attributes and/or structures of the graph. In recent years, graph neural networks (GNNs) have been studied extensively and have successfully performed difficult machine learning tasks in node classification, link prediction, and graph classification thanks to the… 

Figures and Tables from this paper



One-class graph neural networks for anomaly detection in attributed networks

One-class graph neural network (OCGNN), a one-class classification framework for graph anomaly detection, which is designed to combine the powerful representation ability of graph neural networks along with the classical one- class objective.

Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs

This paper proposes StrGNN, an end-to-end structural temporal Graph Neural Network model for detecting anomalous edges in dynamic graphs and fully implements and deploys it into a real enterprise security system, and it greatly helps detect advanced threats and optimize the incident response.

ComGA: Community-Aware Attributed Graph Anomaly Detection

A novel community-aware attributed graph anomaly detection framework (ComGA), designed to improve the performance of anomaly detection, and a tailored deep graph convolutional network (tGCN) to anomaly detection on attributed graphs.

A Synergistic Approach for Graph Anomaly Detection With Pattern Mining and Feature Learning

A synergistic approach that leverages pattern mining to inform the GNN algorithms on how to aggregate local information through connections to capture the global patterns and performs significantly better than existing graph anomaly detection methods.

A Flexible Attentive Temporal Graph Networks for Anomaly Detection in Dynamic Networks

  • Dali ZhuYuchen MaYinlong Liu
  • Computer Science
    2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)
  • 2020
A novel framework DynAD is proposed for anomalous edge detection on time-evolving networks, which performs adaptive parameter learning in an end-to-end manner and significantly outperforms the state-of-the-art baseline methods in anomaly detection.

A Comprehensive Survey on Graph Anomaly Detection with Deep Learning

A taxonomy that follows a task-driven strategy and categorizes existing work according to the anomalous graph objects that they can detect is provided, and 12 future research directions spanning unsolved and emerging problems introduced by graph data, anomaly detection, deep learning and real-world applications are highlighted.

ANEMONE: Graph Anomaly Detection with Multi-Scale Contrastive Learning

A novel graph anomaly detection framework, namely ANEMONE, to simultaneously identify the anomalies in multiple graph scales and employs a statistical anomaly estimator to evaluate the abnormality of each node according to the degree of agreement from multiple perspectives.

Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection

This paper proposes a novel method, Self-Supervised Learning for Graph Anomaly Detection (SL-GAD), which outperforms state-of-the-art methods by a large margin and employs two modules, generative attribute regression and multi-view contrastive learning for anomaly detection.

Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation

This work introduces a novel deep anomaly detection approach for GAD that learns rich global and local normal pattern information by joint random distillation of graph and node representations.

Graph Neural Network-Based Anomaly Detection in Multivariate Time Series

This approach combines a structure learning approach with graph neural networks, additionally using attention weights to provide explainability for the detected anomalies.