mlsanityData to 7 Oct 2026

Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values

arXiv 2401.05800 ↗First posted 11 Jan 2024cs.LG cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

The detection of anomalies in multivariate time series data is crucial for various practical applications, including smart power grids, traffic flow forecasting, and industrial process control. However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training; (2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values. In this work, we introduce a novel framework called GST-Pro, which utilizes a graph spatiotemporal process and anomaly scorer to tackle the aforementioned challenges in detecting anomalies on irregularly-sampled multivariate time series. Our approach comprises two main components. First, we propose a graph spatiotemporal process based on neural controlled differential equations. This process enables effective modeling of multivariate time series from both spatial and temporal perspectives, even when the data contains missing values. Second, we present a novel distribution-based anomaly scoring mechanism that alleviates the reliance on complete uniform observations. By analyzing the predictions of the graph spatiotemporal process, our approach allows anomalies to be easily detected. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods, regardless of whether there are missing values present in the data. Our code is available: https://github.com/huankoh/GST-Pro.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 32 of its 61 references that are in the map. First posted on arXiv 11 Jan 2024.

Builds on

32 of 61 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  4. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 663
  5. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 563
  6. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  7. 2018Invertible Residual Networkscited by 364
  8. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  9. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  10. 2016Structured Sequence Modeling with Graph Convolutional Recurrent Networkscited by 273
  11. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
  12. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
20 more
  1. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  2. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  3. 2021Graph Neural Controlled Differential Equations for Traffic Forecastingcited by 133
  4. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
  5. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  6. 2017Attend and Diagnose: Clinical Time Series Analysis using Attention Modelscited by 105
  7. 2021Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoTcited by 104
  8. 2015Characterizing Concept Driftcited by 93
  9. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  10. 2022An Empirical Survey on Long Document Summarization: Datasets, Models and Metricscited by 74
  11. 2022Multivariate Time Series Forecasting with Dynamic Graph Neural ODEscited by 72
  12. 2021An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Seriescited by 68
  13. 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
  14. 2022How Far are We from Robust Long Abstractive Summarization?cited by 25
  15. 2023Learning from data with structured missingnesscited by 24
  16. 2023Integrating Graphs with Large Language Models: Methods and Prospectscited by 18
  17. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 17
  18. 2023Unraveling Privacy Risks of Individual Fairness in Graph Neural Networkscited by 16
  19. 2020Multivariate Time Series Classification with Hierarchical Variational Graph Poolingcited by 12
  20. 2020Isolation Distributional Kernel: A New Tool for Point & Group Anomaly Detectioncited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 3.

10 papers.

  1. 2025TimeOmni-1: Incentivizing Complex Reasoning with Time Series in Large Language Modelscited by 24
  2. 2024A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classificationcited by 9
  3. 2024Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classificationcited by 7
  4. 2025Boundary-enhanced time series data imputation with long-term dependency diffusion modelscited by 2
  5. 2026Securing Time Integrity in Energy IoT Against Clock Drift and Y2K38 Failurescited by 1
  6. 2025Robust Spatiotemporally Contiguous Anomaly Detection Using Tensor Decompositioncited by 0
  7. 2025CLEANet: Robust and Efficient Anomaly Detection in Contaminated Multivariate Time Seriescited by 0
  8. 2025Dynamic Reward Scaling for Multivariate Time Series Anomaly Detection: A VAE-Enhanced Reinforcement Learning Approachcited by 0
  9. 2026Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learningcited by 0
  10. 2026GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputationcited by 0