Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning

Bruna Alves, Armando J. Pinho, Sónia Gouveia

Abstract

The topic of Multivariate Time Series Anomaly Detection (MTSAD) has grown rapidly over the past years, with a steady rise in publications and Deep Learning (DL) models becoming the dominant paradigm. To address the lack of systematization in the field, this study introduces a novel and unified taxonomy with eleven dimensions over three parts (Input, Output and Model) for the categorization of DL-based MTSAD methods. The dimensions were established in a two-fold approach. First, they derived from a comprehensive analysis of methodological studies. Second, insights from review papers were incorporated. Furthermore, the proposed taxonomy was validated using an additional set of recent publications, providing a clear overview of methodological trends in MTSAD. Results reveal a convergence toward Transformer-based and reconstruction and prediction models, setting the foundation for emerging adaptive and generative trends. Building on and complementing existing surveys, this unified taxonomy is designed to accommodate future developments, allowing for new categories or dimensions to be added as the field progresses. This work thus consolidates fragmented knowledge in the field and provides a reference point for future research in MTSAD.

Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning

Abstract

The topic of Multivariate Time Series Anomaly Detection (MTSAD) has grown rapidly over the past years, with a steady rise in publications and Deep Learning (DL) models becoming the dominant paradigm. To address the lack of systematization in the field, this study introduces a novel and unified taxonomy with eleven dimensions over three parts (Input, Output and Model) for the categorization of DL-based MTSAD methods. The dimensions were established in a two-fold approach. First, they derived from a comprehensive analysis of methodological studies. Second, insights from review papers were incorporated. Furthermore, the proposed taxonomy was validated using an additional set of recent publications, providing a clear overview of methodological trends in MTSAD. Results reveal a convergence toward Transformer-based and reconstruction and prediction models, setting the foundation for emerging adaptive and generative trends. Building on and complementing existing surveys, this unified taxonomy is designed to accommodate future developments, allowing for new categories or dimensions to be added as the field progresses. This work thus consolidates fragmented knowledge in the field and provides a reference point for future research in MTSAD.
Paper Structure (27 sections, 23 equations, 7 figures, 1 table)

This paper contains 27 sections, 23 equations, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Concepts, Methods and Benchmarks in MTSAD
  3. Types of anomalies: temporal versus inter-metric
  4. Problem Formulation in MTSAD
  5. Evaluation of an MTSAD methodology
  6. Benchmark MTSAD methodologies and datasets
  7. Taxonomy of DL-based approaches for MTSAD
  8. Paper screening and selection criteria
  9. Publication trends in MTSAD
  10. The proposed taxonomy on MTSAD
  11. Insights from prior research
  12. Overview of the Literature on the Dimensions of the New Taxonomy
  13. Input: Preprocessing, Format and Content
  14. Output: Type, Thresholding and Granularity
  15. Model: Task and Loss Function
  16. ...and 12 more sections

Figures (7)

  • Figure 1: Examples of temporal anomalies in synthetic MTS generated with https://github.com/datamllab/tods/tree/benchmark/benchmark/synthetic/Generator: (A) Point anomaly in metrics 1 and 2, (B) Contextual in metric 1, (C) Collective in metric 1 and (D) Collective spanning metric 3. The anomaly in (C) is also inter-metric.
  • Figure 2: Schematic representation of the process of learning a regression model $f$. In case of a classification model, the output of the model would be $\hat{y}$ and the loss function would compare it with the know target $y$, $\mathcal{L}(y,\hat{y})$.
  • Figure 3: Illustration of the point-adjustment (PA) strategy showing ground truth, model output and adjusted output over time points (circles). Image adapted from ElAmineSehili2024.
  • Figure 4: Annual number of documents retrieved using the search query. A total of 1,040 documents were retrieved, including 142 before 2019 and 898 from 2019 to 2024. The red-shaded area highlights the 2019–2024 period, which marks a significant growth in publication volume. Chart directly retrieved and adapted from Scopus ® (https://www.scopus.com/).
  • Figure 5: Distribution of the 898 Scopus documents screened from the 2019-2024 period into eligible (green) and excluded (red) categories. Among the 464 eligible, 393 correspond to DL-based methods, the focus of this review. The 434 excluded were based on six criteria (12, 86, 168, 106, 50, 12).
  • ...and 2 more figures