Anomalous Change Point Detection Using Probabilistic Predictive Coding
This addresses scalability and interpretability issues in change point and anomaly detection for fields like medical imaging and time series analysis, though it appears incremental as it builds on deep learning methods.
The paper tackles the problem of change point and anomaly detection in complex data by proposing Probabilistic Predictive Coding (PPC), which learns low-dimensional latent representations and predictions to compute interpretable anomaly scores, achieving linear time complexity and demonstrating effectiveness across synthetic time series, image data, and real-world magnetic resonance spectroscopic imaging data.
Change point detection (CPD) and anomaly detection (AD) are essential techniques in various fields to identify abrupt changes or abnormal data instances. However, existing methods are often constrained to univariate data, face scalability challenges with large datasets due to computational demands, and experience reduced performance with high-dimensional or intricate data, as well as hidden anomalies. Furthermore, they often lack interpretability and adaptability to domain-specific knowledge, which limits their versatility across different fields. In this work, we propose a deep learning-based CPD/AD method called Probabilistic Predictive Coding (PPC) that jointly learns to encode sequential data to low dimensional latent space representations and to predict the subsequent data representations as well as the corresponding prediction uncertainties. The model parameters are optimized with maximum likelihood estimation by comparing these predictions with the true encodings. At the time of application, the true and predicted encodings are used to determine the probability of conformity, an interpretable and meaningful anomaly score. Furthermore, our approach has linear time complexity, scalability issues are prevented, and the method can easily be adjusted to a wide range of data types and intricate applications. We demonstrate the effectiveness and adaptability of our proposed method across synthetic time series experiments, image data, and real-world magnetic resonance spectroscopic imaging data.