mlsanityData to 7 Oct 2026

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

arXiv 1811.08055 ↗First posted 20 Nov 2018cs.LG stat.MLcited by 181

Not on the map. Why?

Abstract (arXiv)

Nowadays, multivariate time series data are increasingly collected in various real world systems, e.g., power plants, wearable devices, etc. Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes. Building such a system, however, is challenging since it not only requires to capture the temporal dependency in each time series, but also need encode the inter-correlations between different pairs of time series. In addition, the system should be robust to noise and provide operators with different levels of anomaly scores based upon the severity of different incidents. Despite the fact that a number of unsupervised anomaly detection algorithms have been developed, few of them can jointly address these challenges. In this paper, we propose a Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to perform anomaly detection and diagnosis in multivariate time series data. Specifically, MSCRED first constructs multi-scale (resolution) signature matrices to characterize multiple levels of the system statuses in different time steps. Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns. Finally, based upon the feature maps which encode the inter-sensor correlations and temporal information, a convolutional decoder is used to reconstruct the input signature matrices and the residual signature matrices are further utilized to detect and diagnose anomalies. Extensive empirical studies based on a synthetic dataset and a real power plant dataset demonstrate that MSCRED can outperform state-of-the-art baseline methods.

Key facts. Cited by 181 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 40; 2023: 48; 2024: 26; 2025: 28; 2026: 18.

181 papers.

Sort:

By area:

  1. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  2. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 130
  3. 2021Graph-Guided Network for Irregularly Sampled Multivariate Time Seriescited by 110
  4. 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 95
  5. 2021An Evaluation of Anomaly Detection and Diagnosis in Multivariate Time Seriescited by 68
  6. 2022TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysiscited by 48
  7. 2022Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformercited by 47
  8. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  9. 2021Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signalscited by 41
  10. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 39
  11. 2023ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detectioncited by 38
  12. 2021Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Versioncited by 35
38 more
  1. 2021Time Series Anomaly Detection for Cyber-Physical Systems via Neural System Identification and Bayesian Filteringcited by 31
  2. 2021Convolutional Transformer based Dual Discriminator Generative Adversarial Networks for Video Anomaly Detectioncited by 31
  3. 2021Dynamic Gaussian Mixture based Deep Generative Model For Robust Forecasting on Sparse Multivariate Time Seriescited by 30
  4. 2024A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challengescited by 29
  5. 2024Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detectioncited by 26
  6. 2025Harnessing Vision Models for Time Series Analysis: A Surveycited by 26
  7. 2023AnomalyBERT: Self-Supervised Transformer for Time Series Anomaly Detection using Data Degradation Schemecited by 25
  8. 2023Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Seriescited by 24
  9. 2023Large Pre-trained time series models for cross-domain Time series analysis taskscited by 22
  10. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  11. 2023MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detectioncited by 20
  12. 2022Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detectioncited by 18
  13. 2023Graph Anomaly Detection in Time Series: A Surveycited by 18
  14. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 17
  15. 2023Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstructioncited by 17
  16. 2024Position: Quo Vadis, Unsupervised Time Series Anomaly Detection?cited by 17
  17. 2022Sintel: A Machine Learning Framework to Extract Insights from Signalscited by 16
  18. 2023CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detectioncited by 15
  19. 2023Label-Free Multivariate Time Series Anomaly Detectioncited by 14
  20. 2022Detecting Anomalies within Time Series using Local Neural Transformationscited by 12
  21. 2022Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalographycited by 11
  22. 2022dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classificationcited by 11
  23. 2023Unsupervised Deep Learning for IoT Time Seriescited by 11
  24. 2023RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervisioncited by 11
  25. 2023Time Series Anomaly Detection using Diffusion-based Modelscited by 11
  26. 2022Functional Anomaly Detection: a Benchmark Studycited by 10
  27. 2022Graph-Time Convolutional Neural Networks: Architecture and Theoretical Analysiscited by 10
  28. 2023Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detectioncited by 10
  29. 2024Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Valuescited by 10
  30. 2024Sub-Adjacent Transformer: Improving Time Series Anomaly Detection with Reconstruction Error from Sub-Adjacent Neighborhoodscited by 10
  31. 2022An Attention-based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Seriescited by 9
  32. 2023LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detectioncited by 9
  33. 2025Towards Foundation Models for Zero-Shot Time Series Anomaly Detection: Leveraging Synthetic Data and Relative Context Discrepancycited by 9
  34. 2022Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoisingcited by 8
  35. 2022A Causal Approach to Detecting Multivariate Time-series Anomalies and Root Causescited by 8
  36. 2023Learnable Path in Neural Controlled Differential Equationscited by 8
  37. 2022Self-supervised Pretraining and Transfer Learning Enable Flu and COVID-19 Predictions in Small Mobile Sensing Datasetscited by 7
  38. 2023Multivariate Time Series Anomaly Detection via Dynamic Graph Forecastingcited by 7

50 most cited of 181 All 181 (JSON)