Filling out the missing gaps: Time Series Imputation with Semi-Supervised Learning
This addresses missing data issues in time series analysis, which can affect tasks like classification, but it appears incremental as it builds on existing imputation methods with a semi-supervised approach.
The paper tackles the problem of missing data in time series by proposing ST-Impute, a semi-supervised imputation method that uses both unlabeled and labeled data, and reports that it outperforms existing supervised and unsupervised methods in imputation quality and downstream tasks.
Missing data in time series is a challenging issue affecting time series analysis. Missing data occurs due to problems like data drops or sensor malfunctioning. Imputation methods are used to fill in these values, with quality of imputation having a significant impact on downstream tasks like classification. In this work, we propose a semi-supervised imputation method, ST-Impute, that uses both unlabeled data along with downstream task's labeled data. ST-Impute is based on sparse self-attention and trains on tasks that mimic the imputation process. Our results indicate that the proposed method outperforms the existing supervised and unsupervised time series imputation methods measured on the imputation quality as well as on the downstream tasks ingesting imputed time series.