CoChat

Exathlon: a benchmark for explainable anomaly detection over time series

Jacob, Vincent, Song, Fei, Stiegler, Arnaud, Rad, Bijan, Diao, Yanlei, Tatbul, Nesime · 2021 · Proceedings of the VLDB Endowment
Cited by 80

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Abstract

Access to high-quality data repositories and benchmarks have been instrumental in advancing the state of the art in many experimental research domains. While advanced analytics tasks over time series data have been gaining lots of attention, lack of such community resources severely limits scientific progress. In this paper, we present Exathlon, the first comprehensive public benchmark for explainable anomaly detection over high-dimensional time series data. Exathlon has been systematically constructed based on real data traces from repeated executions of large-scale stream processing jobs on an Apache Spark cluster. Some of these executions were intentionally disturbed by introducing instances of six different types of anomalous events (e.g., misbehaving inputs, resource contention, process failures). For each of the anomaly instances, ground truth labels for the root cause interval as well as those for the extended effect interval are provided, supporting the development and evaluation of a wide range of anomaly detection (AD) and explanation discovery (ED) tasks. We demonstrate the practical utility of Exathlon's dataset, evaluation methodology, and end-to-end data science pipeline design through an experimental study with three state-of-the-art AD and ED techniques.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.14778/3476249.3476307

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 7 references

Research works printed but not linked: 47

  1. 10.5555/1316689.1316732 · doi:10.5555/1316689.1316732
  2. Bagnall Anthony J., 1811, The UEA Multivariate Time Series Classification Archive, 2018
  3. 10.1145/3035918.3035928 · DOI · Paper page
  4. 10.5555/3454287.3455135 · doi:10.5555/3454287.3455135
  5. 10.1109/MS.2016.60 · DOI · Paper page
  6. 10.1145/3399579.3399865 · DOI
  7. 10.1002/for.768 · DOI · Paper page
  8. Boniol Paul, 2020, Automated Anomaly Detection in Large Sequences. In IEEE 36th International Conference on Data Engineering (ICDE). 1834--1837
  9. 10.14778/3407790.3407792 · DOI
  10. Bontemps Loïc, 2016, Collective Anomaly Detection Based on Long Short-Term Memory Recurrent Neural Networks. In International Conference on Future Data and Security Engineering (FDSE), 10018
  11. Chalapathy Raghavendra, 2019, Deep Learning for Anomaly Detection: A Survey. CoRR abs/1901.03407 · arXiv
  12. 10.1145/3352020.3352024 · DOI · Paper page
  13. 10.1145/1807128.1807152 · DOI · Paper page
  14. Dau Hoang Anh, 2018, Yan Zhu, Shaghayegh Gharghabi, Chotirat Ann Ratanamahatana, and Eamonn J. Keogh.
  15. Dua Dheeru, The UCI Machine Learning Repository
  16. 10.14778/2735461.2735467 · doi:10.14778/2735461.2735467
  17. 10.1145/2500853.2500858 · DOI · Paper page
  18. Frosst Nicholas, International Workshop on Comprehensibility and Explanation in AI and ML.
  19. 10.1145/2463676.2463712 · DOI · Paper page
  20. 10.5555/530588 · doi:10.5555/530588
  21. 10.5555/2621979 · doi:10.5555/2621979
  22. Hinton Geoffrey, 2006, Reducing the Dimensionality of Data with Neural Networks. Science 313, 5786
  23. 10.1145/3299869.3314048 · DOI
  24. 10.1145/1594977.1592597 · DOI · Paper page
  25. 10.1016/j.eswa.2020.113187 · DOI
  26. 10.1145/2939672.2939874 · DOI · Paper page
  27. Lavin Alexander, 2015, Evaluating Real-Time Anomaly Detection Algorithms - The Numenta Anomaly Benchmark. In IEEE International Conference on Machine Learning and Applications (ICMLA). 38--44
  28. 10.1145/2389241.2389246 · DOI
  29. 10.1145/2133360.2133363 · DOI · Paper page
  30. 10.5555/3295222.3295230 · doi:10.5555/3295222.3295230
  31. 10.14778/3389133.3389136 · DOI · Paper page
  32. Malhotra Pankaj, 2015, Long Short Term Memory Networks for Anomaly Detection in Time Series. In European Symposium on Artificial Neural Networks (ESANN). 89--94
  33. Rabl Tilmann, 2019, TPC Technology Conference on Performance Evaluation and Benchmarking (TPCTC). 47--63
  34. Rayana Shebuti, 2021, Outlier Detection DataSets
  35. 10.1145/2939672.2939778 · DOI · Paper page
  36. Ribeiro Marco Túlio, 2018, Anchors: High-Precision Model-Agnostic Explanations. AAAI Conference.
  37. 10.14778/2856318.2856329 · DOI
  38. Singh Nidhi, 2017, Demystifying Numenta Anomaly Benchmark. In International Joint Conference on Neural Networks (IJCNN). 1570--1577
  39. 10.5555/3305890.3306024 · doi:10.5555/3305890.3306024
  40. 10.5555/3326943.3327120 · doi:10.5555/3326943.3327120
  41. 10.14778/2994509.2994526 · DOI
  42. Wang Alex, GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding. In International Conference on Learning Representations (ICLR).
  43. 10.14778/2536354.2536356 · DOI · Paper page
  44. Wu Mike, 2018, Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. AAAI Conference.
  45. 10.1145/3178876.3185996 · DOI · Paper page
  46. 10.1145/3371425.3371427 · DOI · Paper page
  47. Zhang Haopeng, 2017, EXstream: Explaining Anomalies in Event Stream Monitoring. In International Conference on Extending Database Technology (EDBT). 156--167

Cited by

See all 80

Metadata

Authors
Jacob, V., Song, F., Stiegler, A., Rad, B., Diao, Y., & Tatbul, N.
Venue
Proceedings of the VLDB Endowment
Published
2021-07
Volume
14
Issue
11
Pages
2613-2626
ISSN
2150-8097 (ISSN-L)
OpenAlex
W3198800015
Cited by
80
References
7
FWCI
4.32
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Exathlon: a benchmark for explainable anomaly detection over time series. https://app.cochat.ai/papers/10.14778/3476249.3476307
The paper
Jacob, V., Song, F., Stiegler, A., Rad, B., Diao, Y., & Tatbul, N. (2021). Exathlon: a benchmark for explainable anomaly detection over time series. Proceedings of the VLDB Endowment. https://doi.org/10.14778/3476249.3476307

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.