mlsanityData to 14 Oct 2026

Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version

arXiv 2111.11108 ↗First posted 22 Nov 2021cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

With the sweeping digitalization of societal, medical, industrial, and scientific processes, sensing technologies are being deployed that produce increasing volumes of time series data, thus fueling a plethora of new or improved applications. In this setting, outlier detection is frequently important, and while solutions based on neural networks exist, they leave room for improvement in terms of both accuracy and efficiency. With the objective of achieving such improvements, we propose a diversity-driven, convolutional ensemble. To improve accuracy, the ensemble employs multiple basic outlier detection models built on convolutional sequence-to-sequence autoencoders that can capture temporal dependencies in time series. Further, a novel diversity-driven training method maintains diversity among the basic models, with the aim of improving the ensemble's accuracy. To improve efficiency, the approach enables a high degree of parallelism during training. In addition, it is able to transfer some model parameters from one basic model to another, which reduces training time. We report on extensive experiments using real-world multivariate time series that offer insight into the design choices underlying the new approach and offer evidence that it is capable of improved accuracy and efficiency. This is an extended version of "Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles", to appear in PVLDB 2022.

Key facts. Cited by 35 papers in the map (data through 14 Oct 2026). Builds on 17 of its 61 references that are in the map. First posted on arXiv 22 Nov 2021.

Builds on

17 of 61 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  5. 2016Language Modeling with Gated Convolutional Networkscited by 702
  6. 2017Convolutional Sequence to Sequence Learningcited by 552
  7. 2018Born Again Neural Networkscited by 546
  8. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  9. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 410
  10. 2017Snapshot Ensembles: Train 1, get M for freecited by 350
  11. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
  12. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 215
5 more
  1. 2018A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Datacited by 182
  2. 2021Unsupervised Path Representation Learning with Curriculum Negative Samplingcited by 42
  3. 2021Graph Attention Recurrent Neural Networks for Correlated Time Series Forecasting -- Full versioncited by 24
  4. 2016Variational Inference for On-line Anomaly Detection in High-Dimensional Time Seriescited by 12
  5. 2020Time Series Data Cleaning: From Anomaly Detection to Anomaly Repairing (Technical Report)cited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 5; 2024: 10; 2025: 5; 2026: 7.

35 papers.

Sort:

  1. 2024TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methodscited by 249
  2. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 131
  3. 2024DUET: Dual Clustering Enhanced Multivariate Time Series Forecastingcited by 107
  4. 2023DCdetector: Dual Attention Contrastive Representation Learning for Time Series Anomaly Detectioncited by 103
  5. 2022Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Versioncited by 59
  6. 2022Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting--Full Versioncited by 59
  7. 2023LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Versioncited by 50
  8. 2021AutoCTS: Automated Correlated Time Series Forecasting -- Extended Versioncited by 48
  9. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 40
  10. 2024Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoderscited by 38
  11. 2023TSGBench: Time Series Generation Benchmarkcited by 26
  12. 2023Navigating the Metric Maze: A Taxonomy of Evaluation Metrics for Anomaly Detection in Time Seriescited by 24
23 more
  1. 2022Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Versioncited by 19
  2. 2024MultiRC: Joint Learning for Time Series Anomaly Prediction and Detection with Multi-scale Reconstructive Contrastcited by 19
  3. 2022Weakly-supervised Temporal Path Representation Learning with Contrastive Curriculum Learning -- Extended Versioncited by 15
  4. 2024Fully Automated Correlated Time Series Forecasting in Minutescited by 12
  5. 2025CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modelingcited by 12
  6. 2024TEAM: Topological Evolution-aware Framework for Traffic Forecasting--Extended Versioncited by 10
  7. 2025K2VAE: A Koopman-Kalman Enhanced Variational AutoEncoder for Probabilistic Time Series Forecastingcited by 8
  8. 2024QCore: Data-Efficient, On-Device Continual Calibration for Quantized Models -- Extended Versioncited by 7
  9. 2024Orca: Ocean Significant Wave Height Estimation with Spatio-temporally Aware Large Language Modelscited by 6
  10. 2024Towards Controllable Time Series Generationcited by 4
  11. 2022Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecastingcited by 3
  12. 2023A Survey of Time Series Anomaly Detection Methods in the AIOps Domaincited by 2
  13. 2025Data Driven Decision Making with Time Series and Spatio-temporal Datacited by 2
  14. 2024Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detectioncited by 1
  15. 2025A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detectioncited by 1
  16. 2026TimeRadar: A Domain-Rotatable Foundation Model for Time Series Anomaly Detectioncited by 1
  17. 2026RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithmscited by 1
  18. 2025VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detectioncited by 0
  19. 2026Multivariate Time-series Anomaly Detection via Dynamic Model Pool & Ensemblingcited by 0
  20. 2026Analyzing Shapley Additive Explanations to Understand Anomaly Detection Algorithm Behaviors and Their Complementaritycited by 0
  21. 2026LEFT: Learnable Fusion of Tri-view Tokens for Unsupervised Time Series Anomaly Detectioncited by 0
  22. 2026Automatic Unsupervised Ensemble Outlier Model Selection--Extended Versioncited by 0
  23. 2026Impute On-Demand: Adaptive Correlated Time Series Imputation for Changing Environmentscited by 0