An End-to-End Model for Time Series Classification In the Presence of Missing Values

TL;DR

This paper introduces an end-to-end neural network model for time series classification that effectively handles missing data by integrating imputation and feature learning, prioritizing classification accuracy over imputation precision.

Contribution

The study presents a novel unified framework that combines data imputation and classification, leveraging label information to improve performance on incomplete time series data.

Findings

Outperforms state-of-the-art methods on 68 UCR datasets.

Effective in scenarios with high missing data ratios.

Demonstrates robustness across univariate and multivariate datasets.

Abstract

Time series classification with missing data is a prevalent issue in time series analysis, as temporal data often contain missing values in practical applications. The traditional two-stage approach, which handles imputation and classification separately, can result in sub-optimal performance as label information is not utilized in the imputation process. On the other hand, a one-stage approach can learn features under missing information, but feature representation is limited as imputed errors are propagated in the classification process. To overcome these challenges, this study proposes an end-to-end neural network that unifies data imputation and representation learning within a single framework, allowing the imputation process to take advantage of label information. Differing from previous methods, our approach places less emphasis on the accuracy of imputation data and instead prioritizes classification performance. A specifically designed multi-scale feature learning module is implemented to extract useful information from the noise-imputation data. The proposed model is evaluated on 68 univariate time series datasets from the UCR archive, as well as a multivariate time series dataset with various missing data ratios and 4 real-world datasets with missing information. The results indicate that the proposed model outperforms state-of-the-art approaches for incomplete time series classification, particularly in scenarios with high levels of missing data.