Contrastive learning-based multi-view clustering for incomplete multivariate time series

Abstract

Incomplete multivariate time series (MTS) clustering is a prevalent research topic in time series analysis, aimed at partitioning MTS containing missing data into distinct clusters. Contrastive learning-based multi-view clustering methods are a promising approach to address this issue. However, existing methods are typically not designed for time series. Specifically, most of these methods struggle to capture the inherent properties of time series, and are susceptible to losing their interdimensional correlations, thereby compromising data integrity. Furthermore, they commonly utilize data augmentation techniques to generate sample pairs for contrastive learning. These existing data augmentation techniques are not suitable for time series, and introduce uncertainty factors, which can diminish the representation learning capacity of contrastive learning. To address the challenges, we propose a contrastive learning-based multi-view clustering method for incomplete multivariate time series (MVCIMTS). In this method, each variable within the MTS is treated as a separate view, enabling a multi-view learning approach. To better leverage the intrinsic information of time series, we utilize a GRU-based model architecture that integrates imputation and clustering within a unified deep learning framework. In this way, missing views can be effectively inferred, and representations suitable for clustering can be learned, thereby enhancing the clustering performance for incomplete time series. Furthermore, we introduce an innovative contrastive learning approach specifically tailored for MTS, which ensures that the exploration of common semantics and clustering consistency across views remains unaffected by uncertainty factors. It assumes that each time series variable within the same sample has similar representations, thereby taking into account the correlation between variables and enhancing the quality of the representations. To the best of our knowledge, this is the first attempt at applying contrastive learning-based multi-view deep clustering to incomplete MTS. We conduct extensive comparative experiments with five multi-view clustering methods and two time series clustering methods on seven benchmark datasets. The results demonstrate that our proposed method is superior to other state-of-the-art methods.