BRATI: Bidirectional Recurrent Attention for Time-Series Imputation
This addresses the challenge of reliable imputation for downstream applications in time-series analysis, representing a strong specific gain rather than a foundational advancement.
The paper tackles the problem of missing data in multivariate time-series analysis by introducing BRATI, a deep-learning model that combines bidirectional recurrent networks and attention mechanisms, and it shows that BRATI consistently outperforms state-of-the-art models in accuracy and robustness across various missing-data scenarios.
Missing data in time-series analysis poses significant challenges, affecting the reliability of downstream applications. Imputation, the process of estimating missing values, has emerged as a key solution. This paper introduces BRATI, a novel deep-learning model designed to address multivariate time-series imputation by combining Bidirectional Recurrent Networks and Attention mechanisms. BRATI processes temporal dependencies and feature correlations across long and short time horizons, utilizing two imputation blocks that operate in opposite temporal directions. Each block integrates recurrent layers and attention mechanisms to effectively resolve long-term dependencies. We evaluate BRATI on three real-world datasets under diverse missing-data scenarios: randomly missing values, fixed-length missing sequences, and variable-length missing sequences. Our findings demonstrate that BRATI consistently outperforms state-of-the-art models, delivering superior accuracy and robustness in imputing multivariate time-series data.