Bayesian tensor autoencoder improves multi-dimensional time series anomaly detection
Bayesian Tensor Autoencoder with Physics-informed Predictive Prior for Multi-dimensional Time Series Anomaly Detection
Machine Learning
Summary
Detecting unusual patterns in complex time series data is challenging because many methods ignore relationships within the data’s multiple dimensions. The authors designed a new method that keeps these internal connections intact by using a tensor-based approach, which treats the data as multi-dimensional arrays. They combined prediction and reconstruction techniques using a Bayesian method and added physical rules about the data's structure to improve accuracy. Their experiments show this approach better detects anomalies in real-world datasets.
What this means in practice
- •For industrial monitoring teams: Detect abnormal events in complex sensor data from machines by preserving intrinsic data relationships for more reliable fault detection.
- •For smart grid operators: Identify unusual patterns in multi-dimensional power usage data to improve reliability and prevent outages.
Authors
Jianan Liu, Chunguang Li
Abstract
Multi-dimensional time series, inherently tensorial, are common in practice. Despite great progress in time series anomaly detection, most existing methods are confined to uni-/multi-variate time series. When handling multi-dimensional time series using these methods, reshaping operations are required, which inevitably break the intrinsic correlations and thus lead to performance degradation. In uni-/multi-variate time series anomaly detection, AutoEncoders (AEs) are widely adopted and generally categorized into reconstruction-based and prediction-based AEs. The reconstruction-based AE utilizes the current observation for reconstruction, while the prediction-based AE utilizes the historical information to predict the current observation. Thus, the two AEs utilize different information. To bridge the gap between reconstruction-based and prediction-based AEs, so as to fully leverage the available information and thus further enhance performance, we propose a predictive prior and incorporate it into the reconstruction-based AE. It may not be very difficult to conceive this idea, but designing the predictive prior so that it can work for tensor anomaly detection is non-trivial. Specifically, to avoid breaking the intrinsic correlations within the multi-dimensional time series, we use the tensor AE as the backbone. To incorporate the predictive prior into the reconstruction-based AE, we propose a Bayesian fusion approach and our analysis reveals that this approach can enhance the modeling capability of the model for normal data. To mitigate the over-generalization problem of AE, we incorporate physical laws, i.e. tensor low-rank decomposition rules, into the neural networks in the predictive prior, leading to the Physics-informed Predictive Prior Tensor AE (PPPTAE) framework. Experimental results on real-world datasets demonstrate the effectiveness of the proposed method.