{"type":"ScholarlyArticle","title":"Deep into Hypersphere: Robust and Unsupervised Anomaly Discovery in Dynamic Networks","authors":[{"name":"Xian Teng","slug":"xian-teng","given":"Xian","family":"Teng","affiliation":"School of Computing and Information , University of Pittsburgh , USA"},{"name":"Muheng Yan","slug":"muheng-yan","given":"Muheng","family":"Yan","affiliation":"School of Computing and Information , University of Pittsburgh , USA"},{"name":"Ali Mert Ertugrul","slug":"ali-mert-ertugrul","given":"Ali Mert","family":"Ertugrul","affiliation":"School of Computing and Information , University of Pittsburgh , USA; Graduate School of Informatics , Middle East Technical University , Turkey"},{"name":"Yu-Ru Lin","slug":"yu-ru-lin","given":"Yu-Ru","family":"Lin","affiliation":"School of Computing and Information , University of Pittsburgh , USA"}],"abstract":"The increasing and flexible use of autonomous systems in many domains -- from intelligent transportation systems, information systems, to business transaction management -- has led to challenges in understanding the \"normal\" and \"abnormal\" behaviors of those systems. As the systems may be composed of internal states and relationships among sub-systems, it requires not only warning users to anomalous situations but also provides \"transparency\" about how the anomalies deviate from normalcy for more appropriate intervention. We propose a unified anomaly discovery framework \"DeepSphere\" that simultaneously meet the above two requirements -- identifying the anomalous cases and further exploring the cases' anomalous structure localized in spatial and temporal context. DeepSphere leverages deep autoencoders and hypersphere learning methods, having the capability of isolating anomaly pollution and reconstructing normal behaviors. DeepSphere does not rely on human annotated samples and can generalize to unseen data. Extensive experiments on both synthetic and real datasets demonstrate the consistent and robust performance of the proposed method.","doi":"10.24963/ijcai.2018/378","url":"https://ijcai.org/proceedings/2018/378","pdf":"https://ijcai.org/proceedings/2018/0378.pdf","markdown":"https://ijcai.org/proceedings/2018/378.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/378","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Machine Learning","track":"Main track","number":378,"pages":{"first":2724,"last":2730},"keywords":["Machine Learning: Unsupervised Learning","Machine Learning: Interpretability","Machine Learning: Time-series;Data Streams","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Baytas et al., 2017] Inci M. Baytas, Cao Xiao, et al. Pa- tient subtyping via time-aware lstm networks. In SIGKDD, pages 65-74. ACM, 2017.","title":"Patient subtyping via time-aware lstm networks","authors":"Inci M Baytas, Cao Xiao","year":"2017","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Braham and Droogenbroeck, 2016] Marc Braham and Marc Van Droogenbroeck. Deep background subtraction with scene-specific convolutional neural networks. In IWSSIP, pages 1-4. IEEE, 2016.","title":"Deep background subtraction with scene-specific convolutional neural networks","authors":"Droogenbroeck Braham, Marc Braham, Marc Van Droogenbroeck","year":"2016","venue":"IWSSIP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Breunig et al., 2000] Markus M. Breunig, Hans-Peter Kriegel, et al. Lof: identifying density-based local outliers. In SIGMOD, volume 29, pages 93-104. ACM, 2000.","title":"Lof: identifying density-based local outliers","authors":"Markus M Breunig, Hans-Peter Kriegel","year":"2000","venue":"SIGMOD","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chalapathy et al., 2017] Raghavendra Chalapathy, Aditya K. Menon, and Sanjay Chawla. Robust, deep and inductive anomaly detection. arXiv preprint arXiv:1704.06743, 2017.","title":"Robust, deep and inductive anomaly detection","authors":"Raghavendra Chalapathy, Aditya K Menon, Sanjay Chawla","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chen and Neill, 2014] Feng Chen and Daniel B. Neill. Non- parametric scan statistics for event detection and forecast- ing in heterogeneous social media graphs. In SIGKDD, pages 1166-1175. ACM, 2014.","title":"Nonparametric scan statistics for event detection and forecasting in heterogeneous social media graphs","authors":"Chen, Neill ; ] Feng Chen, Daniel B Neill","year":"2014","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cheng et al., 2016] Wei Cheng, Kai Zhang, et al. Rank- ing causal anomalies via temporal and dynamical analysis on vanishing correlations. In SIGKDD, pages 805-814. ACM, 2016.","title":"Ranking causal anomalies via temporal and dynamical analysis on vanishing correlations","authors":"Wei Cheng, Kai Zhang","year":"2016","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Crescenzo et al., 2017] Cristiano Di Crescenzo, Giulia Gavazzi, et al. Hermevent: a news collection for emerging- event detection. In WIMS, page 11. ACM, 2017.","title":"Hermevent: a news collection for emergingevent detection","authors":"Cristiano Di Crescenzo, Giulia Gavazzi","year":"2017","venue":"WIMS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Denil et al., 2012] Misha Denil, Loris Bazzani, et al. Learn- ing where to attend with deep architectures for image tracking. Neural Computation, 24(8):2151-2184, 2012.","title":"Learning where to attend with deep architectures for image tracking","authors":"Misha Denil, Loris Bazzani","year":"2012","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Erfani et al., 2016] Sarah M. Erfani, Sutharshan Ra- jasegarar, et al. High-dimensional and large-scale anomaly detection using a linear one-class svm with deep learning. Pattern Recognition, 58:121-134, 2016.","title":"High-dimensional and large-scale anomaly detection using a linear one-class svm with deep learning","authors":"M Sarah, ; Erfani","year":"2016","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Khan and Madden, 2009] Shehroz S. Khan and Michael G. Madden. A survey of recent trends in one class classifica- tion. In AICS, pages 188-197. Springer, 2009.","title":"A survey of recent trends in one class classification","authors":"S Shehroz, Michael G Khan, Madden","year":"2009","venue":"AICS","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kingma and Ba, 2014] Diederik Kingma and Jimmy Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.","title":"Adam: A method for stochastic optimization","authors":"Diederik Kingma, Jimmy Ba","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[LeCun et al., 2015] Yann LeCun, Yoshua Bengio, and Ge- offrey Hinton. Deep learning. Nature, 521(7553):436, 2015.","title":"Deep learning","authors":"Yann Lecun, Yoshua Bengio, Geoffrey Hinton","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2016] Jun Liu, Amir Shahroudy, et al. Spatio- temporal lstm with trust gates for 3d human action recog- nition. In ECCV, pages 816-833. Springer, 2016.","title":"Spatiotemporal lstm with trust gates for 3d human action recognition","authors":"Liu","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Malhotra et al., 2015] Pankaj Malhotra, Lovekesh Vig, et al. Long short term memory networks for anomaly de- tection in time series. In Proceedings, page 89. Presses universitaires de Louvain, 2015.","title":"Long short term memory networks for anomaly detection in time series","authors":"Pankaj Malhotra, Lovekesh Vig","year":"2015","venue":"Proceedings","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Malhotra et al., 2016] Pankaj Malhotra, Anusha Ramakr- ishnan, et al. Lstm-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148, 2016.","title":"Lstm-based encoder-decoder for multi-sensor anomaly detection","authors":"Pankaj Malhotra, Anusha Ramakrishnan","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mongiovi et al., 2013] Misael Mongiovi, Petko Bogdanov, et al. Netspot: Spotting significant anomalous regions on dynamic networks. In ICDM, pages 28-36. SIAM, 2013.","title":"Netspot: Spotting significant anomalous regions on dynamic networks","authors":"Misael Mongiovi, Petko Bogdanov","year":"2013","venue":"ICDM","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ranshous et al., 2015] Stephen Ranshous, Shitian Shen, et al. Anomaly detection in dynamic networks: a survey. Wiley Interdisciplinary Reviews: Computational Statistics, 7(3):223-247, 2015.","title":"Anomaly detection in dynamic networks: a survey","authors":"Stephen Ranshous, Shitian Shen","year":"2015","venue":"Wiley Interdisciplinary Reviews: Computational Statistics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rozenshtein et al., 2014] Polina Rozenshtein, Aris Anag- nostopoulos, et al. Event detection in activity networks. In SIGKDD, pages 1176-1185. ACM, 2014.","title":"Event detection in activity networks","authors":"Aris Polina Rozenshtein, Anagnostopoulos","year":"2014","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schölkopf et al., 2000] Bernhard Schölkopf, Robert Williamson, et al. Support vector method for novelty detection. In NIPS, pages 582-588, 2000.","title":"Support vector method for novelty detection","authors":"Bernhard Schölkopf, Robert Williamson","year":"2000","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sun et al., 2007] Jimeng Sun, Spiros Papadimitriou, et al. Graphscope: parameter-free mining of large time-evolving graphs. In SIGKDD, pages 687-696. ACM, 2007.","title":"Graphscope: parameter-free mining of large time-evolving graphs","authors":"Sun","year":"2007","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tax and Duin, 2004] David M.J. Tax and Robert P.W. Duin. Support vector data description. Machine Learning, 54(1):45-66, 2004.","title":"Support vector data description","authors":"M J David, Tax, P W Robert, Duin","year":"2004","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Teng et al., 2017] Xian Teng, Yu-Ru Lin, and Xidao Wen. Anomaly detection in dynamic networks using multi-view time-series hypersphere learning. In CIKM, pages 827- 836. ACM, 2017.","title":"Anomaly detection in dynamic networks using multi-view time-series hypersphere learning","authors":"Xian Teng, Yu-Ru Lin, Xidao Wen","year":"2017","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhou and Paffenroth, 2017] Chong Zhou and Randy C. Paf- fenroth. Anomaly detection with robust deep autoen- coders. In SIGKDD, pages 665-674. ACM, 2017.","title":"Paffenroth. Anomaly detection with robust deep autoencoders","authors":"Chong Zhou, Randy C","year":"2017","venue":"SIGKDD","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}