BRATI: Bidirectional Recurrent Attention for Time-Series Imputation

TL;DR

BRATI is a new deep-learning model that improves multivariate time-series data imputation by combining bidirectional recurrent networks and attention mechanisms, effectively capturing long-term dependencies and feature correlations.

Contribution

This paper introduces BRATI, a novel bidirectional recurrent attention model that enhances time-series imputation by addressing long-term dependencies and feature correlations.

Findings

BRATI outperforms existing models in accuracy across multiple datasets.

BRATI demonstrates robustness under various missing-data scenarios.

The model effectively captures both short-term and long-term dependencies.

Abstract

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.