Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles

With the sweeping digitalization of societal, medical, industrial, and scientific processes, sensing technologies are being deployed that produce increasing volumes of time series data, thus fueling a plethora of new or improved applications. In this setting, outlier detection is frequently important, and while solutions based on neural networks exist, they leave room for improvement in terms of both accuracy and efficiency. With the objective of achieving such improvements, we propose a diversity-driven, convolutional ensemble. To improve accuracy, the ensemble employs multiple basic outlier detection models built on convolutional sequence-tosequence autoencoders that can capture temporal dependencies in time series. Further, a novel diversity-driven training method maintains diversity among the basic models, with the aim of improving the ensemble's accuracy. To improve efficiency, the approach enables a high degree of parallelism during training. In addition, it is able to transfer some model parameters from one basic model to another, which reduces training time. We report on extensive experiments using real-world multivariate time series that offer insight into the design choices underlying the new approach and offer evidence that it is capable of improved accuracy and efficiency.

Automated summary

This paper proposes a diversity-driven, convolutional ensemble method to improve the accuracy and efficiency of outlier detection in time series data. The method utilizes multiple basic models and a novel training approach to enhance accuracy, while enabling high parallelism and parameter transfer during training to improve efficiency. Extensive experiments with real-world multivariate time series demonstrate the capability of the approach to achieve improved accuracy and efficiency.