Multi-view Anomaly Detection via Probabilistic Latent Variable Models
This work addresses multi-view anomaly detection, which is important for applications like sensor networks or medical imaging, but it appears incremental as it extends probabilistic canonical correlation analysis.
The paper tackles the problem of detecting anomalies in multi-view data by proposing a nonparametric Bayesian probabilistic latent variable model that distinguishes between normal instances with a single latent vector and anomalous ones with multiple latent vectors, achieving effectiveness in anomaly detection and missing value imputation.
We propose a nonparametric Bayesian probabilistic latent variable model for multi-view anomaly detection, which is the task of finding instances that have inconsistent views. With the proposed model, all views of a non-anomalous instance are assumed to be generated from a single latent vector. On the other hand, an anomalous instance is assumed to have multiple latent vectors, and its different views are generated from different latent vectors. By inferring the number of latent vectors used for each instance with Dirichlet process priors, we obtain multi-view anomaly scores. The proposed model can be seen as a robust extension of probabilistic canonical correlation analysis for noisy multi-view data. We present Bayesian inference procedures for the proposed model based on a stochastic EM algorithm. The effectiveness of the proposed model is demonstrated in terms of performance when detecting multi-view anomalies and imputing missing values in multi-view data with anomalies.