Inductive Multi-view Semi-Supervised Anomaly Detection via Probabilistic Modeling

This paper considers anomaly detection with multi-view data. Unlike traditional detection on single-view data which identifies anomalies based on inconsistency between instances, multi-view anomaly detection identifies anomalies based on view inconsistency within each instance. Current multi-view detection approaches are mostly unsupervised and transductive. This may have limited performance in many applications, which have labeled normal data and prefer efficient detection on new data. In this paper, we propose an inductive semi-supervised multi-view anomaly detection approach. We design a probabilistic generative model for normal data, which assumes different views of a normal instance are generated from a shared latent factor, conditioned on which the views become independent. We estimate the model by maximizing its likelihood on normal data using the EM algorithm. Then, we apply the model to detect anomalies, which are instances generated with small probabilities. We experiment our approach on nine public data sets under different multi-view anomaly settings, and show it outperforms several state-of-the-art multi-view detection methods.

[1]  Robert B. Fisher,et al.  Semi-supervised Learning for Anomalous Trajectory Detection , 2008, BMVC.

[2]  Deepak S. Turaga,et al.  A Spectral Framework for Detecting Inconsistency across Multi-source Object Relationships , 2011, 2011 IEEE 11th International Conference on Data Mining.

[3]  Tomoharu Iwata,et al.  Clustering-based anomaly detection in multi-view data , 2013, CIKM.

[4]  Rajesh P. N. Rao,et al.  Learning Shared Latent Structure for Image Synthesis and Robotic Imitation , 2005, NIPS.

[5]  Gilles Blanchard,et al.  Semi-Supervised Novelty Detection , 2010, J. Mach. Learn. Res..

[6]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[7]  Michael I. Jordan,et al.  A Probabilistic Interpretation of Canonical Correlation Analysis , 2005 .

[8]  Dung N. Lam,et al.  Using Consensus Clustering for Multi-view Anomaly Detection , 2012, 2012 IEEE Symposium on Security and Privacy Workshops.

[9]  Yixin Chen,et al.  Automatic Feature Decomposition for Single View Co-training , 2011, ICML.

[10]  Handong Zhao,et al.  Dual-Regularized Multi-View Outlier Detection , 2015, IJCAI.

[11]  Yun Fu,et al.  Latent Discriminant Subspace Representations for Multi-View Outlier Detection , 2018, AAAI.

[12]  Thomas G. Dietterich,et al.  Open Category Detection with PAC Guarantees , 2018, ICML.

[13]  Tomoharu Iwata,et al.  Multi-view Anomaly Detection via Robust Probabilistic Latent Variable Models , 2016, NIPS.

[14]  Neil D. Lawrence,et al.  Gaussian Process Latent Variable Models for Visualisation of High Dimensional Data , 2003, NIPS.

[15]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[16]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[17]  Ming Shao,et al.  Multi-View Low-Rank Analysis for Outlier Detection , 2015, SDM.

[18]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.