mlsanityData to 7 Oct 2026

Is it worth it? Comparing six deep and classical methods for unsupervised anomaly detection in time series

arXiv 2212.11080 ↗First posted 21 Dec 2022cs.LG cs.AI cs.IRcited by 9

Not on the map. Why?

Abstract (arXiv)

Detecting anomalies in time series data is important in a variety of fields, including system monitoring, healthcare, and cybersecurity. While the abundance of available methods makes it difficult to choose the most appropriate method for a given application, each method has its strengths in detecting certain types of anomalies. In this study, we compare six unsupervised anomaly detection methods of varying complexity to determine whether more complex methods generally perform better and if certain methods are better suited to certain types of anomalies. We evaluated the methods using the UCR anomaly archive, a recent benchmark dataset for anomaly detection. We analyzed the results on a dataset and anomaly type level after adjusting the necessary hyperparameters for each method. Additionally, we assessed the ability of each method to incorporate prior knowledge about anomalies and examined the differences between point-wise and sequence-wise features. Our experiments show that classical machine learning methods generally outperform deep learning methods across a range of anomaly types.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 17 of its 49 references that are in the map. First posted on arXiv 21 Dec 2022.

Builds on

17 of 49 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 423
  4. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  5. 2019Deep Learning for Anomaly Detection: A Surveycited by 357
  6. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  7. 2022TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Datacited by 211
  8. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
  9. 2020A review on outlier/anomaly detection in time series datacited by 187
  10. 2019MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscited by 176
  11. 2020Multivariate Time-series Anomaly Detection via Graph Attention Networkcited by 165
  12. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
5 more
  1. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  2. 2015Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmarkcited by 87
  3. 2020Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Artcited by 55
  4. 2022Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Seriescited by 42
  5. 2018Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detectioncited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 0; 2026: 3.

9 papers.

  1. 2023Explainable Time Series Anomaly Detection using Masked Latent Generative Modelingcited by 15
  2. 2023Deep Anomaly Detection on Tennessee Eastman Process Datacited by 5
  3. 2024FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Datacited by 3
  4. 2024DeepHYDRA: Resource-Efficient Time-Series Anomaly Detection in Dynamically-Configured Systemscited by 1
  5. 2024Unraveling Anomalies in Time: Unsupervised Discovery and Isolation of Anomalous Behavior in Bio-regenerative Life Support System Telemetrycited by 1
  6. 2024PATH: A Discrete-sequence Dataset for Evaluating Online Unsupervised Anomaly Detection Approaches for Multivariate Time Seriescited by 1
  7. 2026Bridging Classification and Reconstruction: Cooperative Time Series Anomaly Detectioncited by 0
  8. 2026Identifying Explicit Parsimonious Piece-wise Polynomial Relationships in Industrial time-series: Application to manipulator robotscited by 0
  9. 2026Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detectioncited by 0