mlsanityData to 7 Oct 2026

RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data

arXiv 2503.18385 ↗First posted 24 Mar 2025cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

The accumulation of time-series signals and the absence of labels make time-series Anomaly Detection (AD) a self-supervised task of deep learning. Methods based on normality assumptions face the following three limitations: (1) A single assumption could hardly characterize the whole normality or lead to some deviation. (2) Some assumptions may go against the principle of AD. (3) Their basic assumption is that the training data is uncontaminated (free of anomalies), which is unrealistic in practice, leading to a decline in robustness. This paper proposes a novel robust approach, RoCA, which is the first to address all of the above three challenges, as far as we are aware. It fuses the separated assumptions of one-class classification and contrastive learning in a single training process to characterize a more complete so-called normality. Additionally, it monitors the training data and computes a carefully designed anomaly score throughout the training process. This score helps identify latent anomalies, which are then used to define the classification boundary, inspired by the concept of outlier exposure. The performance on AIOps datasets improved by 6% compared to when contamination was not considered (COCA). On two large and high-dimensional multivariate datasets, the performance increased by 5% to 10%. RoCA achieves the highest average performance on both univariate and multivariate datasets. The source code is available at https://github.com/ruiking04/RoCA.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 30 of its 50 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

30 of 50 references.

References · 30

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  7. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  8. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  10. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  11. 2018Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholdingcited by 407
  12. 2021Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancycited by 387
18 more
  1. 2021Time-Series Representation Learning via Temporal and Contextual Contrastingcited by 342
  2. 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 223
  3. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 213
  4. 2019Time-Series Anomaly Detection Service at Microsoftcited by 163
  5. 2020Current Time Series Anomaly Detection Benchmarks are Flawed and are Creating the Illusion of Progresscited by 148
  6. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  7. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  8. 2021Towards a Rigorous Evaluation of Time-series Anomaly Detectioncited by 95
  9. 2015Evaluating Real-time Anomaly Detection Algorithms - the Numenta Anomaly Benchmarkcited by 87
  10. 2022Local Evaluation of Time Series Anomaly Detection Algorithmscited by 79
  11. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  12. 2021Neural Contextual Anomaly Detection for Time Seriescited by 42
  13. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 39
  14. 2019Robust Anomaly Detection in Images using Adversarial Autoencoderscited by 38
  15. 2021Merlion: A Machine Learning Library for Time Seriescited by 25
  16. 2020Simple and Effective Prevention of Mode Collapse in Deep One-Class Classificationcited by 16
  17. 2021Contrastive Predictive Coding for Anomaly Detectioncited by 10
  18. 2022Deep Contrastive One-Class Time Series Anomaly Detectioncited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025This Time is Different: An Observability Perspective on Time Series Foundation Modelscited by 57
  2. 2025CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environmentscited by 0
  3. 2025An Improved Time Series Anomaly Detection by Applying Structural Similaritycited by 0
  4. 2026Multi-Modal Anomaly Detection: A Surveycited by 0