Anomaly Detection in Dynamic Graphs: A Comprehensive Survey
Обнаружение аномалий в динамических графах: всесторонний обзор
2024-05-29
SCID: 54.1/63eyf3rq
Discuss with AI
deep learningdynamic graph anomaly detectiondynamic networksgraph-based anomaly detectionmatrix transformations
Figures from the paper
Abstract (AI)
This survey article presents a comprehensive and conceptual overview of anomaly detection (AD) using dynamic graphs. We focus on existing graph-based AD techniques and their applications to dynamic networks. The contributions of this survey article include the following: (i) a comparative study of existing surveys on AD; (ii) a Dynamic Graph-based anomaly detection (DGAD) review framework in which approaches for detecting anomalies in dynamic graphs are grouped based on traditional machine learning models, matrix transformations, probabilistic approaches, and deep learning approaches; (iii) a discussion of graphically representing both discrete and dynamic networks; and (iv) a discussion of the advantages of graph-based techniques for capturing the relational structure and complex interactions in dynamic graph data. Finally, this work identifies the potential challenges and future directions for detecting anomalies in dynamic networks. This DGAD survey approach aims to provide a valuable resource for researchers and practitioners by summarizing the strengths and limitations of each approach, highlighting current research trends, and identifying open challenges. In doing so, it can guide future research efforts and promote advancements in AD in dynamic graphs.
Key Findings
1
DGAD approaches are categorized into traditional machine learning, matrix transformation, probabilistic, and deep learning methods.
2
Graph-based methods are highlighted for capturing relational structure and complex interactions in dynamic graph data.
3
The survey compares existing anomaly detection surveys and discusses representations of both discrete and continuously evolving networks.
4
The survey identifies strengths, limitations, open challenges, and future research directions for anomaly detection in dynamic networks.
5
The survey introduces a Dynamic Graph-based Anomaly Detection (DGAD) review framework for organizing existing dynamic-graph anomaly detection methods.
Research Object
Dynamic graphs and networks
Research Subject
Anomaly detection techniques, applications, strengths, limitations, and open challenges for capturing anomalies in relational structures and complex interactions over time
Publication Details
Publication Date
2024-05-29
Journal
Publisher
ISSN
Cited by
101
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai17
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Semi-Supervised Classification with Graph Convolutional Networks2016
Generative adversarial networks2020
Anomaly detection: A survey2009
The Graph Neural Network Model2008
Effective Approaches to Attention-based Neural Machine Translation2015
Graph neural networks: A review of methods and applications2020
Deep Learning for Anomaly Detection: A Review2021
Heterogeneous Graph Attention Network2019
Self-Attention with Relative Position Representations2018
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network2019
Graph Neural Networks: A Review of Methods and Applications2018
Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoT2021
A comprehensive survey of anomaly detection techniques for high dimensional big data2020
Foundations and Modeling of Dynamic Networks Using Dynamic Graph Neural Networks: A Survey2021
Graph Anomaly Detection With Graph Neural Networks: Current Status and Challenges2022
Targeted Branching for the Maximum Independent Set Problem Using Graph Neural Networks2024