{"type":"ScholarlyArticle","title":"Neural Contextual Anomaly Detection for Time Series","authors":[{"name":"Chris U. Carmona","slug":"chris-u-carmona","given":"Chris U.","family":"Carmona","affiliation":"Amazon Research"},{"name":"François-Xavier Aubet","slug":"francois-xavier-aubet","given":"François-Xavier","family":"Aubet","affiliation":"Amazon Research"},{"name":"Valentin Flunkert","slug":"valentin-flunkert","given":"Valentin","family":"Flunkert","affiliation":"Amazon Research"},{"name":"Jan Gasthaus","slug":"jan-gasthaus","given":"Jan","family":"Gasthaus","affiliation":"Amazon Research"}],"abstract":"We introduce Neural Contextual Anomaly Detection (NCAD), a framework for anomaly detection on time series that scales seamlessly from the unsupervised to supervised setting, and is applicable to both univariate and multivariate time series. This is achieved by combining recent developments in representation learning for multivariate time series, with techniques for deep anomaly detection originally developed for computer vision that we tailor to the time series setting. Our window-based approach facilitates learning the boundary between normal and anomalous classes by injecting generic synthetic anomalies into the available data. NCAD can effectively take advantage of domain knowledge and of any available training labels. We demonstrate empirically on standard benchmark datasets that our approach obtains a state-of-the-art performance in the supervised, semi-supervised, and unsupervised settings.","doi":"10.24963/ijcai.2022/394","url":"https://ijcai.org/proceedings/2022/394","pdf":"https://ijcai.org/proceedings/2022/0394.pdf","markdown":"https://ijcai.org/proceedings/2022/394.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/394","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":394,"pages":{"first":2843,"last":2851},"keywords":["Data Mining: Anomaly/Outlier Detection","Machine Learning: Time-series; Data Streams"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986673","length_sec":89,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984816","length_sec":354,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Aubet et al., 2021] Franc ¸ois-Xavier Aubet, Daniel Zügner, and Jan Gasthaus. Monte carlo em for deep time se- ries anomaly detection. arXiv preprint arXiv:2112.14436, 2021.","title":"Franc ¸ois-Xavier Aubet, Daniel Zügner, and Jan Gasthaus. Monte carlo em for deep time se-ries anomaly detection","authors":"Aubet","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Audibert et al., 2020] Julien Audibert, Pietro Michiardi, Frédéric Guyard, Sébastien Marti, and Maria A Zuluaga. Usad: Unsupervised anomaly detection on multivariate time series. In 26th ACM SIGKDD, 2020.","title":"Usad: Unsupervised anomaly detection on multivariate time series","authors":"Julien Audibert, Pietro Michiardi, Frédéric Guyard, Sébastien Marti, Maria A Zuluaga","year":"2020","venue":"26th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ayed et al., 2020] Fadhel Ayed, Lorenzo Stella, Tim Januschowski, and Jan Gasthaus. Anomaly detection at scale: The case for deep distributional time series models. arXiv preprint arXiv:2007.15541, 2020.","title":"Anomaly detection at scale: The case for deep distributional time series models","authors":"Fadhel Ayed, Lorenzo Stella, Tim Januschowski, Jan Gasthaus","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bock et al., 2022] Christian Bock, Franc ¸ois-Xavier Aubet, Jan Gasthaus, Andrey Kan, Ming Chen, and Laurent Cal- lot. Online time series anomaly detection with state space gaussian processes. arXiv preprint arXiv:2201.06763, 2022.","title":"Online time series anomaly detection with state space gaussian processes","authors":"Bock","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Breunig et al., 2000] Markus M Breunig, Hans-Peter Kriegel, Raymond T Ng, and Jörg Sander. Lof: iden- tifying density-based local outliers. In ACM SIGMOD, 2000.","title":"Lof: identifying density-based local outliers","authors":"Markus M Breunig, Hans-Peter Kriegel, Raymond T Ng, Jörg Sander","year":"2000","venue":"ACM SIGMOD","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ehrlich et al., 2021] Elena Ehrlich, Laurent Callot, and Franc ¸ois-Xavier Aubet. Spliced binned-pareto distribu- tion for robust modeling of heavy-tailed time series. arXiv preprint arXiv:2106.10952, 2021.","title":"Spliced binned-pareto distribution for robust modeling of heavy-tailed time series","authors":"Elena Ehrlich, Laurent Callot, Franc ¸ois-Xavier Aubet","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Franceschi et al., 2019] Jean Yves Franceschi, Aymeric Dieuleveut, and Martin Jaggi. Unsupervised scalable rep- resentation learning for multivariate time series. In Pro- ceedings of the 33th Conference on Neural Information Processing Systems, NeurIPS, 2019.","title":"Unsupervised scalable representation learning for multivariate time series","authors":"Franceschi","year":"2019","venue":"Proceedings of the 33th Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gao et al., 2020] Jingkun Gao, Xiaomin Song, Qingsong Wen, Pichao Wang, and et al. RobustTAD: Ro- bust Time Series Anomaly Detection via Decomposi- tion and Convolutional Neural Networks. arXiv preprint arXiv:2002.09545, 2020.","title":"RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks","authors":"Gao","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hendrycks et al., 2019] Dan Hendrycks, Mantas Mazeika, and Thomas Dietterich. Deep anomaly detection with out- lier exposure. In ICLR, 2019.","title":"Deep anomaly detection with outlier exposure","authors":"Dan Hendrycks, Mantas Mazeika, Thomas Dietterich","year":"2019","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Hundman et al., 2018] Kyle Hundman, Valentino Con- stantinou, Christopher Laporte, Ian Colwell, and Tom Soderstrom. Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding. In 24th ACM SIGKDD, 2018.","title":"Detecting spacecraft anomalies using lstms and nonparametric dynamic thresholding","authors":"Kyle Hundman, Valentino Constantinou, Christopher Laporte, Ian Colwell, Tom Soderstrom","year":"2018","venue":"24th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kim et al., 2022] Siwon Kim, Kukjin Choi, Hyun-Soo Choi, Byunghan Lee, and Sungroh Yoon. Towards a rig- orous evaluation of time-series anomaly detection. In Pro- ceedings of the 36th AAAI Conference on Artificial Intelli- gence, AAAI-22, 2022.","title":"Towards a rigorous evaluation of time-series anomaly detection","authors":"Kim","year":"2022","venue":"Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI-22","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lavin and Ahmad, 2015] Alexander Lavin and Subutai Ah- mad. Evaluating real-time anomaly detection algorithms- the numenta anomaly benchmark. In IEEE 14th ICMLA, 2015.","title":"Evaluating real-time anomaly detection algorithmsthe numenta anomaly benchmark","authors":"Ahmad ; Lavin, Alexander Lavin, Subutai Ahmad","year":"2015","venue":"IEEE 14th ICMLA","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2019] Dan Li, Dacheng Chen, Baihong Jin, Lei Shi, Jonathan Goh, and See-Kiong Ng. Mad-gan: Mul- tivariate anomaly detection for time series data with gen- erative adversarial networks. In ICANN, 2019.","title":"Mad-gan: Multivariate anomaly detection for time series data with generative adversarial networks","authors":"Dan Li, Dacheng Chen, Baihong Jin, Lei Shi, Jonathan Goh, See-Kiong Ng","year":"2019","venue":"ICANN","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2008] Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. Isolation forest. In 2008 eighth ieee international conference on data mining. IEEE, 2008.","title":"Isolation forest","authors":"Tony Fei, Kai Liu, Ming Ting, Zhi-Hua Zhou","year":"2008","venue":"2008 eighth ieee international conference on data mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2015] Dapeng Liu, Youjian Zhao, Haowen Xu, Yongqian Sun, and et al. Opprentice: Towards practical and automatic anomaly detection through machine learn- ing. In Proceedings of the 2015 Internet Measurement Conference, 2015.","title":"Opprentice: Towards practical and automatic anomaly detection through machine learning","authors":"Dapeng Liu, Youjian Zhao, Haowen Xu, Yongqian Sun","year":"2015","venue":"Proceedings of the 2015 Internet Measurement Conference","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Park et al., 2018] Daehyung Park, Yuuna Hoshi, and Charles C Kemp. A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational au- toencoder. IEEE Robotics and Automation Letters, 2018.","title":"A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder","authors":"Park","year":"2018","venue":"IEEE Robotics and Automation Letters","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ren et al., 2019] Hansheng Ren, Bixiong Xu, Yujing Wang, Chao Yi, and et al. Time-Series Anomaly Detection Ser- vice at Microsoft. In 25th ACM SIGKDD, 2019.","title":"Time-Series Anomaly Detection Service at Microsoft","authors":"Ren","year":"2019","venue":"25th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ruff et al., 2018] Lukas Ruff, Robert A Vandermeulen, Nico Görnitz, Lucas Deecke, and et al. Deep One-Class Classification. In ICML, 2018.","title":"Deep One-Class Classification","authors":"Lukas Ruff, Robert A Vandermeulen, Nico Görnitz, Lucas Deecke","year":"2018","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ruff et al., 2020a] Lukas Ruff, Robert A Vandermeulen, Billy Joe Franks, Klaus-Robert Müller, and Marius Kloft. Rethinking assumptions in deep anomaly detection. arXiv preprint arXiv:2006.00339, 2020.","title":"Rethinking assumptions in deep anomaly detection","authors":"Ruff","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ruff et al., 2020b] Lukas Ruff, Robert A Vandermeulen, Nico Görnitz, Alexander Binder, and et al. Deep Semi- Supervised Anomaly Detection. In ICLR, 2020.","title":"Deep Semi-Supervised Anomaly Detection","authors":"Ruff","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ruff et al., 2021] Lukas Ruff, Jacob R. Kauffmann, Robert A. Vandermeulen, Gregoire Montavon, and et al. A Unifying Review of Deep and Shallow Anomaly Detection. Proceedings of the IEEE, 2021.","title":"A Unifying Review of Deep and Shallow Anomaly Detection","authors":"Lukas Ruff, Jacob R Kauffmann, Robert A Vandermeulen, Gregoire Montavon","year":"2021","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Schlegl et al., 2017] Thomas Schlegl, Philipp Seeböck, Se- bastian M Waldstein, Ursula Schmidt-Erfurth, and Georg Langs. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In Inter- national conference on information processing in medical imaging, 2017.","title":"Unsupervised anomaly detection with generative adversarial networks to guide marker discovery","authors":"Thomas Schlegl, Philipp Seeböck, Ursula Sebastian M Waldstein, Georg Schmidt-Erfurth, Langs","year":"2017","venue":"International conference on information processing in medical imaging","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Schölkopf et al., 1999] Bernhard Schölkopf, Robert C Williamson, Alexander J Smola, John Shawe-Taylor, John C Platt, et al. Support vector method for novelty detection. In NIPS 12, 1999.","title":"Support vector method for novelty detection","authors":"Bernhard Schölkopf, Alexander J Robert C Williamson, John Smola, John C Shawe-Taylor, Platt","year":"1999","venue":"NIPS 12","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shen et al., 2020] Lifeng Shen, Zhuocong Li, and James Kwok. Timeseries anomaly detection using temporal hi- erarchical one-class network. In Proceedings of the 34th Conference on Neural Information Processing Systems, NeurIPS, volume 33, 2020.","title":"Timeseries anomaly detection using temporal hierarchical one-class network","authors":"Lifeng Shen, Zhuocong Li, James Kwok","year":"2020","venue":"Proceedings of the 34th Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shewhart, 1931] Walter Andrew Shewhart. Economic Con- trol of Quality of Manufactured Product. Bell Telephone Laboratories series. American Society for Quality Control, 1931.","title":"Economic Control of Quality of Manufactured Product","authors":"Walter Andrew, Shewhart","year":"1931","venue":"Bell Telephone Laboratories series","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Shipmon et al., 2017] Dominique T Shipmon, Jason M Gurevitch, Paolo M Piselli, and Stephen T Edwards. Time series anomaly detection; detection of anomalous drops with limited features and sparse examples in noisy highly periodic data. arXiv preprint arXiv:1708.03665, 2017.","title":"Time series anomaly detection; detection of anomalous drops with limited features and sparse examples in noisy highly periodic data","authors":"Jason M Dominique T Shipmon, Paolo M Gurevitch, Stephen T Piselli, Edwards","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Siffer et al., 2017] Alban Siffer, Pierre-Alain Fouque, Alexandre Termier, and Christine Largouet. Anomaly detection in streams with extreme value theory. In 23rd ACM SIGKDD, 2017.","title":"Anomaly detection in streams with extreme value theory","authors":"Alban Siffer, Pierre-Alain Fouque, Alexandre Termier, Christine Largouet","year":"2017","venue":"23rd ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Smolyakov et al., 2019] D. Smolyakov, N. Sviridenko, V. Ishimtsev, E. Burikov, and E. Burnaev. Learning Ensembles of Anomaly Detectors on Synthetic Data. arXiv:1905.07892 [cs, stat], May 2019.","title":"Learning Ensembles of Anomaly Detectors on Synthetic Data","authors":"D Smolyakov, N Sviridenko, V Ishimtsev, E Burikov, E Burnaev","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Su et al., 2019] Ya Su, Youjian Zhao, Chenhao Niu, Rong Liu, Wei Sun, and Dan Pei. Robust anomaly detection for multivariate time series through stochastic recurrent neural network. In 25th ACM SIGKDD, 2019.","title":"Robust anomaly detection for multivariate time series through stochastic recurrent neural network","authors":"Ya Su, Youjian Zhao, Chenhao Niu, Rong Liu, Wei Sun, Dan Pei","year":"2019","venue":"25th ACM SIGKDD","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Tatbul et al., 2018] Nesime Tatbul, Tae Jun Lee, Stan Zdonik, Mejbah Alam, and Justin Gottschlich. Precision and recall for time series. In Proceedings of the 32th Conference on Neural Information Processing Systems, NeurIPS, 2018.","title":"Precision and recall for time series","authors":"Tatbul","year":"2018","venue":"Proceedings of the 32th Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Tax and Duin, 2004] David MJ Tax and Robert PW Duin. Support vector data description. Machine learning, 2004.","title":"Support vector data description","authors":"M J David, Tax, Robert Pw Duin","year":"2004","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[van den Oord et al., 2016] Aaron van den Oord, Sander Dieleman, Heiga Zen, Karen Simonyan, and et al. WaveNet: A Generative Model for Raw Audio. Techni- cal report, Google, sep 2016.","title":"WaveNet: A Generative Model for Raw Audio","authors":"Oord Van Den","year":"2016","venue":"Technical report","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wu and Keogh, 2020] Renjie Wu and Eamonn J Keogh. Current time series anomaly detection benchmarks are flawed and are creating the illusion of progress. arXiv preprint arXiv:2009.13807, 2020.","title":"Current time series anomaly detection benchmarks are flawed and are creating the illusion of progress","authors":"Renjie Wu, Eamonn J Keogh","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Xu et al., 2018] Haowen Xu, Wenxiao Chen, Nengwen Zhao, Zeyan Li, and et al. Unsupervised anomaly detec- tion via variational auto-encoder for seasonal kpis in web applications. In 2018 WWW Conference, 2018.","title":"Unsupervised anomaly detection via variational auto-encoder for seasonal kpis in web applications","authors":"Xu","year":"2018","venue":"2018 WWW Conference","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yahoo! Labs, 2015] Yahoo! Labs. S5 -A Labeled Anomaly Detection Dataset, version 1.0, 2015.","title":"Yahoo! Labs. S5 -A Labeled Anomaly Detection Dataset","authors":null,"year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhang et al., 2018] Hongyi Zhang, Moustapha Cisse, Yann N Dauphin, and David Lopez-Paz. Mixup: Beyond Empirical Risk Minimization. In ICLR, 2018.","title":"Mixup: Beyond Empirical Risk Minimization","authors":"Hongyi Zhang, Moustapha Cisse, David Yann N Dauphin, Lopez-Paz","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhang et al., 2019] Chuxu Zhang, Dongjin Song, Yuncong Chen, Xinyang Feng, Cristian Lumezanu, Wei Cheng, Jingchao Ni, Bo Zong, Haifeng Chen, and Nitesh V Chawla. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data. AAAI, 2019.","title":"A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data","authors":"Zhang","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Zhao et al., 2020] Hang Zhao, Yujing Wang, Juanyong Duan, Congrui Huang, Defu Cao, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, and Qi Zhang. Multivariate time-series anomaly detection via graph attention network. arXiv preprint arXiv:2009.02040, 2020.","title":"Multivariate time-series anomaly detection via graph attention network","authors":"Hang Zhao, Yujing Wang, Juanyong Duan, Congrui Huang, Defu Cao, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zong et al., 2018] Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, and et al. Deep autoencoding gaus- sian mixture model for unsupervised anomaly detection. In ICLR, 2018.","title":"Deep autoencoding gaussian mixture model for unsupervised anomaly detection","authors":"Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}