A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection
Обзор графовых нейронных сетей для временных рядов: прогнозирование, классификация, импутация и обнаружение аномалий
2024-08-14
SCID: 54.1/gpk3268p
Discuss with AI
anomaly detectiongraph neural networkstime series analysistime series forecastingtime series imputation
Figures from the paper
Abstract (AI)
Time series are the primary data type used to record dynamic system measurements and generated in great volume by both physical sensors and online processes (virtual sensors). Time series analytics is therefore crucial to unlocking the wealth of information implicit in available data. With the recent advancements in graph neural networks (GNNs), there has been a surge in GNN-based approaches for time series analysis. These approaches can explicitly model inter-temporal and inter-variable relationships, which traditional and other deep neural network-based methods struggle to do. In this survey, we provide a comprehensive review of graph neural networks for time series analysis (GNN4TS), encompassing four fundamental dimensions: forecasting, classification, anomaly detection, and imputation. Our aim is to guide designers and practitioners to understand, build applications, and advance research of GNN4TS. At first, we provide a comprehensive task-oriented taxonomy of GNN4TS. Then, we present and discuss representative research works and introduce mainstream applications of GNN4TS. A comprehensive discussion of potential future research directions completes the survey. This survey, for the first time, brings together a vast array of knowledge on GNN-based time series research, highlighting foundations, practical applications, and opportunities of graph neural networks for time series analysis.
Key Findings
1
GNN-based methods explicitly model inter-temporal and inter-variable relationships that traditional and other deep neural networks struggle to represent.
2
It identifies potential future research directions and consolidates foundational knowledge, practical applications, and research opportunities in GNN-based time series analysis.
3
The paper introduces a comprehensive, task-oriented taxonomy of graph neural networks for time series analysis.
4
The survey organizes graph neural network approaches for time series analysis into forecasting, classification, anomaly detection, and imputation.
5
The survey reviews representative research and mainstream applications, providing guidance for designing and deploying GNN-based time series systems.
Research Object
Time series from physical sensors and online processes analyzed with graph neural networks
Research Subject
Graph-based modeling of inter-temporal and inter-variable relationships for time-series forecasting, classification, imputation, and anomaly detection
Publication Details
Publication Date
2024-08-14
Journal
Publisher
ISSN
Cited by
566
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai20
Exploiting Generative AI to Scale up Intelligent Tutoring Systems2023
Semi-Supervised Classification with Graph Convolutional Networks2016
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling2014
A Comprehensive Survey on Graph Neural Networks2020
A Survey of Large Language Models2026
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
Neural Message Passing for Quantum Chemistry2017
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting2019
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network2019
Transformers in Time Series: A Survey2023
Time-series forecasting with deep learning: a survey2021
A Review on Outlier/Anomaly Detection in Time Series Data2021
Discrete Signal Processing on Graphs2013
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series2021
Interaction Networks for Learning about Objects, Relations and Physics2016
Anomaly detection in time series: a comprehensive evaluation2022
Deep Learning for Time Series Anomaly Detection: A Survey2024
Multivariate Time-Series Anomaly Detection via Graph Attention Network2020
Traffic Flow Prediction via Spatial Temporal Graph Neural Network2020
Multivariate Time Series Anomaly Detection and Interpretation using Hierarchical Inter-Metric and Temporal Embedding2021