TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification

TL;DR

TANDEM is a novel neural differential equation framework that uses attention mechanisms to improve time series classification with missing data, outperforming existing methods on multiple datasets.

Contribution

It introduces an attention-guided neural differential equation model that effectively handles missing data without relying on imputation, enhancing classification accuracy and interpretability.

Findings

Outperforms state-of-the-art methods on 30 benchmark datasets.

Provides improved classification accuracy on real-world medical data.

Offers insights into the handling of missing data through attention mechanisms.

Abstract

Handling missing data in time series classification remains a significant challenge in various domains. Traditional methods often rely on imputation, which may introduce bias or fail to capture the underlying temporal dynamics. In this paper, we propose TANDEM (Temporal Attention-guided Neural Differential Equations for Missingness), an attention-guided neural differential equation framework that effectively classifies time series data with missing values. Our approach integrates raw observation, interpolated control path, and continuous latent dynamics through a novel attention mechanism, allowing the model to focus on the most informative aspects of the data. We evaluate TANDEM on 30 benchmark datasets and a real-world medical dataset, demonstrating its superiority over existing state-of-the-art methods. Our framework not only improves classification accuracy but also provides insights into the handling of missing data, making it a valuable tool in practice.