mlsanityData to 7 Oct 2026

Label-Free Multivariate Time Series Anomaly Detection

arXiv 2312.11549 ↗First posted 17 Dec 2023cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Anomaly detection in multivariate time series (MTS) has been widely studied in one-class classification (OCC) setting. The training samples in OCC are assumed to be normal, which is difficult to guarantee in practical situations. Such a case may degrade the performance of OCC-based anomaly detection methods which fit the training distribution as the normal distribution. In this paper, we propose MTGFlow, an unsupervised anomaly detection approach for MTS anomaly detection via dynamic Graph and entity-aware normalizing Flow. MTGFlow first estimates the density of the entire training samples and then identifies anomalous instances based on the density of the test samples within the fitted distribution. This relies on a widely accepted assumption that anomalous instances exhibit more sparse densities than normal ones, with no reliance on the clean training dataset. However, it is intractable to directly estimate the density due to complex dependencies among entities and their diverse inherent characteristics. To mitigate this, we utilize the graph structure learning model to learn interdependent and evolving relations among entities, which effectively captures complex and accurate distribution patterns of MTS. In addition, our approach incorporates the unique characteristics of individual entities by employing an entity-aware normalizing flow. This enables us to represent each entity as a parameterized normal distribution. Furthermore, considering that some entities present similar characteristics, we propose a cluster strategy that capitalizes on the commonalities of entities with similar characteristics, resulting in more precise and detailed density estimation. We refer to this cluster-aware extension as MTGFlow_cluster. Extensive experiments are conducted on six widely used benchmark datasets, in which MTGFlow and MTGFlow cluster demonstrate their superior detection performance.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 34 of its 71 references that are in the map. First posted on arXiv 17 Dec 2023.

Builds on

34 of 71 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2017DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networkscited by 1,004
  8. 2017Masked Autoregressive Flow for Density Estimationcited by 680
  9. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  10. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  11. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
  12. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
22 more
  1. 2021Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecastingcited by 332
  2. 2021CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flowscited by 320
  3. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  4. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  5. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 270
  6. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
  7. 2020Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flowscited by 212
  8. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  9. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 185
  10. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 181
  11. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  12. 2019Guided Image Generation with Conditional Invertible Neural Networkscited by 147
  13. 2020Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flowscited by 142
  14. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  15. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  16. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  17. 2021LUNAR: Unifying Local Outlier Detection Methods via Graph Neural Networkscited by 42
  18. 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
  19. 2021A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Treescited by 26
  20. 2022Detecting Multivariate Time Series Anomalies with Zero Known Labelcited by 21
  21. 2022Multi-scale Attention Flow for Probabilistic Time Series Forecastingcited by 19
  22. 2021Unsupervised Outlier Detection using Memory and Contrastive Learningcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 5.

14 papers.

Sort:

  1. 2024Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detectioncited by 26
  2. 2025Deep Learning Advancements in Anomaly Detection: A Comprehensive Surveycited by 15
  3. 2025FreCT: Frequency-augmented Convolutional Transformer for Robust Time Series Anomaly Detectioncited by 10
  4. 2024DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Seriescited by 7
  5. 2024Deep Multi-Manifold Transformation Based Multivariate Time Series Fault Detectioncited by 0
  6. 2025iADCPS: Time Series Anomaly Detection for Evolving Cyber-physical Systems via Incremental Meta-learningcited by 0
  7. 2025CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environmentscited by 0
  8. 2025Causal Disentanglement Learning for Accurate Anomaly Detection in Multivariate Time Seriescited by 0
  9. 2025Multivariate Time Series Forecasting with Hybrid Euclidean-SPD Manifold Graph Neural Networkscited by 0
  10. 2026CGSTA: Cross-Scale Graph Contrast with Stability-Aware Alignment for Multivariate Time-Series Anomaly Detectioncited by 0
  11. 2026Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detectioncited by 0
  12. 2026VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detectioncited by 0
2 more
  1. 2026RagGAD: Rationale-Aware Conditional Gaussian Mixture Normalizing Flow for Unsupervised Graph Anomaly Detectioncited by 0
  2. 2026Towards Robust Time Series Learning via Capacity-Centric Modulationcited by 0