TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908932251844608 |
|---|---|
| author | Oh, YongKyung Lim, Dong-Young Kim, Sungil Bui, Alex |
| author_facet | Oh, YongKyung Lim, Dong-Young Kim, Sungil Bui, Alex |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_17519 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification Oh, YongKyung Lim, Dong-Young Kim, Sungil Bui, Alex Machine Learning Artificial Intelligence 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. |
| title | TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.17519 |