mlsanityData to 14 Oct 2026

ProtoX-AD: Self-Explainable Time Series Anomaly Detection and Characterization

arXiv 2606.13277 ↗First posted 11 Jun 2026stat.ML cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Recent advances in time series anomaly detection (TSAD) have highlighted the effectiveness of self-supervised classification-based approaches. These methods apply transformations to normal training samples, training a classifier to recognize transformation-specific patterns that help identify anomalies through increased classification errors. Despite their strong performance, a significant challenge is their lack of explainability, as they provide limited insight into the characteristics of flagged anomalies. To address this limitation, we propose ProtoX-AD, a prototype-based self-explainable framework for self-supervised TSAD. ProtoX-AD learns transformation-aware latent representations alongside interpretable prototypes, enabling both accurate anomaly detection and the identification of distinct anomalous profiles through prototype-based explanations. Additionally, it allows for systematic analysis of how transformation design impacts detection performance and explainability. Experimental results on synthetic and real-world datasets demonstrate that ProtoX-AD achieves detection performance comparable to its black-box counterparts while offering more consistent and semantically meaningful explanations than existing explainable baselines. Our code is publicly available at https://github.com/Aitorzan3/ProtoX-AD.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 11 Jun 2026.

Builds on

19 of 34 references.

References · 19

  1. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  2. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  3. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 471
  4. 2018The UCR Time Series Archivecited by 431
  5. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 207
  6. 2022Deep Learning for Time Series Anomaly Detection: A Surveycited by 131
  7. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  8. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  9. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  10. 2022ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Modelcited by 34
  11. 2022Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlookcited by 24
  12. 2020On the Nature and Types of Anomalies: A Review of Deviations in Datacited by 22
7 more
  1. 2023Explainable Time Series Anomaly Detection using Masked Latent Generative Modelingcited by 15
  2. 2022Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalographycited by 11
  3. 2022Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Successcited by 11
  4. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  5. 2023Prototypes as Explanation for Time Series Anomaly Detectioncited by 4
  6. 2025A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open Challengescited by 4
  7. 2025NeuCoReClass AD: Redefining Self-Supervised Time Series Anomaly Detectioncited by 1

Built on by

Not cited yet.