Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series (2404.11269v2)

Published 17 Apr 2024 in cs.LG and cs.AI

Abstract: In time series anomaly detection (TSAD), the scarcity of labeled data poses a challenge to the development of accurate models. Unsupervised domain adaptation (UDA) offers a solution by leveraging labeled data from a related domain to detect anomalies in an unlabeled target domain. However, existing UDA methods assume consistent anomalous classes across domains. To address this limitation, we propose a novel Domain Adaptation Contrastive learning model for Anomaly Detection in multivariate time series (DACAD), combining UDA with contrastive learning. DACAD utilizes an anomaly injection mechanism that enhances generalization across unseen anomalous classes, improving adaptability and robustness. Additionally, our model employs supervised contrastive loss for the source domain and self-supervised contrastive triplet loss for the target domain, ensuring comprehensive feature representation learning and domain-invariant feature extraction. Finally, an effective Centre-based Entropy Classifier (CEC) accurately learns normal boundaries in the source domain. Extensive evaluations on multiple real-world datasets and a synthetic dataset highlight DACAD's superior performance in transferring knowledge across domains and mitigating the challenge of limited labeled data in TSAD.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Usad: Unsupervised anomaly detection on multivariate time series. In SIGKDD, pages 3395–3404, 2020.
  2. Do deep neural networks contribute to multivariate time series anomaly detection? Pattern Recognition, 132:108945, 2022.
  3. Time series domain adaptation via sparse associative structure alignment. In AAAI, volume 35, pages 6859–6867, 2021.
  4. A recurrent latent variable model for sequential data. Advances in neural information processing systems, 28, 2015.
  5. Generative adversarial networks: An overview. IEEE signal processing magazine, 35(1):53–65, 2018.
  6. Deep learning for time series anomaly detection: A survey. arXiv preprint arXiv:2211.05244, 2022.
  7. Carla: Self-supervised contrastive representation learning for time series anomaly detection. arXiv preprint arXiv:2308.09296, 2023.
  8. Graph neural network-based anomaly detection in multivariate time series data. In COMPSAC’2021, pages 1128–1133. IEEE, 2021.
  9. Unsupervised scalable representation learning for multivariate time series. In Advances in Neural Information Processing Systems, volume 32. Curran Associates, Inc., 2019.
  10. Unsupervised domain adaptation by backpropagation. In ICML, pages 1180–1189. PMLR, 2015.
  11. Long short-term memory. Neural computation, 9:1735–1780, 1997.
  12. Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding. In SIGKDD, pages 387–395, 2018.
  13. Supervised contrastive learning. Advances in neural information processing systems, 33:18661–18673, 2020.
  14. Towards a rigorous evaluation of time-series anomaly detection. In AAAI, volume 36, pages 7194–7201, 2022.
  15. Context-aware domain adaptation for time series anomaly detection. In Proceedings of the SDM’2023, pages 676–684. SIAM, 2023.
  16. Temporal convolutional networks: A unified approach to action segmentation. In Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III 14, pages 47–54. Springer, 2016.
  17. Similarity preserving representation learning for time series clustering. In IJCAI, volume 19, pages 2845–2851, 2019.
  18. Deep unsupervised domain adaptation: A review of recent advances and perspectives. APSIPA Transactions on Signal and Information Processing, 11, 2022.
  19. Conditional adversarial domain adaptation. Advances in neural information processing systems, 31, 2018.
  20. A new method for intelligent fault diagnosis of machines based on unsupervised domain adaptation. Neurocomputing, 427:96–109, 2021.
  21. Lstm-based vae-gan for time-series anomaly detection. Sensors, 20:3738, 2020.
  22. Contrastive learning for unsupervised domain adaptation of time series. ICLR, 2023.
  23. A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder. IEEE Robotics and Automation Letters, 3:1544–1551, 2018.
  24. Variational recurrent adversarial deep domain adaptation. In ICLR, 2016.
  25. Contrastive adversarial domain adaptation for machine remaining useful life prediction. IEEE Transactions on Industrial Informatics, 17:5239–5249, 2020.
  26. Deep one-class classification. In ICML, pages 4393–4402. PMLR, 2018.
  27. Anomaly detection in time series: a comprehensive evaluation. Proceedings of the VLDB, 15:1779–1797, 2022.
  28. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 815–823, 2015.
  29. Timeseries anomaly detection using temporal hierarchical one-class network. Advances in Neural Information Processing Systems, 33:13016–13026, 2020.
  30. Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In SIGKDD, pages 2828–2837, 2019.
  31. Unsupervised representation learning for time series with temporal neighborhood coding. In ICLR, 2021.
  32. Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7167–7176, 2017.
  33. Inter-patient ecg arrhythmia heartbeat classification based on unsupervised domain adaptation. Neurocomputing, 454:339–349, 2021.
  34. A survey of unsupervised deep domain adaptation. ACM Transactions on Intelligent Systems and Technology (TIST), 11:1–46, 2020.
  35. Multi-source deep domain adaptation with weak supervision for time-series sensor data. In SIGKDD, pages 1768–1778, 2020.
  36. Anomaly transformer: Time series anomaly detection with association discrepancy. In ICLR, 2022.
  37. Dcdetector: Dual attention contrastive representation learning for time series anomaly detection. In SIGKDD, 2023.
  38. Ts2vec: Towards universal representation of time series. In AAAI, volume 36, pages 8980–8987, 2022.
  39. A transformer-based framework for multivariate time series representation learning. In SIGKDD, pages 2114–2124. Association for Computing Machinery, 2021.
  40. A survey on negative transfer. IEEE/CAA Journal of Automatica Sinica, 10(2):305–329, 2022.
  41. Unsupervised sleep staging system based on domain adaptation. Biomedical Signal Processing and Control, 69:102937, 2021.
  42. Beatgan: Anomalous rhythm detection using adversarially generated time series. In IJCAI, volume 2019, pages 4433–4439, 2019.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Zahra Zamanzadeh Darban (6 papers)
  2. Geoffrey I. Webb (62 papers)
  3. Mahsa Salehi (21 papers)
  4. Yiyuan Yang (25 papers)
  5. Charu C. Aggarwal (29 papers)
  6. Qingsong Wen (139 papers)

Summary

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

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