Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles -- Extended Version
This work addresses outlier detection for applications in societal, medical, industrial, and scientific domains, but it is incremental as it builds on existing neural network solutions.
The paper tackles the problem of unsupervised outlier detection in time series data by proposing a diversity-driven convolutional ensemble, which improves accuracy through multiple autoencoder models and a novel training method, and enhances efficiency via parallelism and parameter transfer, with experiments on real-world data showing improved performance.
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-to-sequence 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. This is an extended version of "Unsupervised Time Series Outlier Detection with Diversity-Driven Convolutional Ensembles", to appear in PVLDB 2022.