Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Prototypes as Explanation for Time Series Anomaly Detection (2307.01601v1)

Published 4 Jul 2023 in cs.LG

Abstract: Detecting abnormal patterns that deviate from a certain regular repeating pattern in time series is essential in many big data applications. However, the lack of labels, the dynamic nature of time series data, and unforeseeable abnormal behaviors make the detection process challenging. Despite the success of recent deep anomaly detection approaches, the mystical mechanisms in such black-box models have become a new challenge in safety-critical applications. The lack of model transparency and prediction reliability hinders further breakthroughs in such domains. This paper proposes ProtoAD, using prototypes as the example-based explanation for the state of regular patterns during anomaly detection. Without significant impact on the detection performance, prototypes shed light on the deep black-box models and provide intuitive understanding for domain experts and stakeholders. We extend the widely used prototype learning in classification problems into anomaly detection. By visualizing both the latent space and input space prototypes, we intuitively demonstrate how regular data are modeled and why specific patterns are considered abnormal.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. Unsupervised real-time anomaly detection for streaming data. Neurocomputing 262 (2017), 134–147.
  2. Counterfactual Explanations for Multivariate Time Series. In 2021 International Conference on Applied Artificial Intelligence (ICAPAI). IEEE, 1–8.
  3. This looks like that: deep learning for interpretable image recognition. arXiv preprint arXiv:1806.10574 (2018).
  4. Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines. IEEE Access (2021).
  5. A comparative study of HTM and other neural network models for online sequence learning with streaming data. In 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 1530–1538.
  6. A survey on concept drift adaptation. ACM computing surveys (CSUR) 46, 4 (2014), 1–37.
  7. Explaining deep classification of time-series data with learned prototypes. In CEUR workshop proceedings, Vol. 2429. NIH Public Access, 15.
  8. Interpretable image recognition with hierarchical prototypes. In Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, Vol. 7. 32–40.
  9. Yangdong He and Jiabao Zhao. 2019. Temporal convolutional networks for anomaly detection in time series. In Journal of Physics: Conference Series, Vol. 1213. IOP Publishing, 042050.
  10. Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining. 387–395.
  11. Generalised Interpretable Shapelets for Irregular Time Series. arXiv preprint arXiv:2005.13948 (2020).
  12. Examples are not enough, learn to criticize! criticism for interpretability. Advances in neural information processing systems 29 (2016).
  13. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).
  14. Efficient shapelet discovery for time series classification. IEEE Transactions on Knowledge and Data Engineering (2020).
  15. Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32.
  16. LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148 (2016).
  17. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426 (2018).
  18. Interpretable and steerable sequence learning via prototypes. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 903–913.
  19. Interpreting Convolutional Sequence Model by Learning Local Prototypes with Adaptation Regularization. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management. 1366–1375.
  20. Time-series anomaly detection service at microsoft. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 3009–3017.
  21. An empirical study of explainable AI techniques on deep learning models for time series tasks. arXiv preprint arXiv:2012.04344 (2020).
  22. Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining. 2828–2837.
  23. Eugen Ursu and Pierre Duchesne. 2009. On modelling and diagnostic checking of vector periodic autoregressive time series models. Journal of Time Series Analysis 30, 1 (2009), 70–96.
  24. Focusing on what is relevant: Time-series learning and understanding using attention. In 2018 24th International Conference on Pattern Recognition (ICPR). IEEE, 2624–2629.
  25. Detecting structural breaks in seasonal time series by regularized optimization. arXiv preprint arXiv:1505.04305 (2015).
  26. Unsupervised anomaly detection via variational auto-encoder for seasonal kpis in web applications. In Proceedings of the 2018 World Wide Web Conference. 187–196.
  27. Deep structured energy based models for anomaly detection. In International Conference on Machine Learning. PMLR, 1100–1109.
  28. ProtGNN: Towards Self-Explaining Graph Neural Networks. arXiv preprint arXiv:2112.00911 (2021).
  29. Deep autoencoding gaussian mixture model for unsupervised anomaly detection. In International Conference on Learning Representations.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now