Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909131956289536 |
|---|---|
| author | Feng, Aosong Chen, Jialin Garza, Juan Berry, Brooklyn Salazar, Francisco Gao, Yifeng Ying, Rex Tassiulas, Leandros |
| author_facet | Feng, Aosong Chen, Jialin Garza, Juan Berry, Brooklyn Salazar, Francisco Gao, Yifeng Ying, Rex Tassiulas, Leandros |
| contents | The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains. To tackle this challenge effectively, it is imperative that the state-of-the-art attention model is scalable to accommodate the growing sequence lengths typically encountered in high-resolution time series data, while also demonstrating robustness in handling the inherent noise prevalent in such datasets. To address this, we propose to hierarchically encode the long time series into multiple levels based on the interaction ranges. By capturing relationships at different levels, we can build more robust, expressive, and efficient models that are capable of capturing both short-term fluctuations and long-term trends in the data. We then propose a new time series transformer backbone (KronTime) by introducing Kronecker-decomposed attention to process such multi-level time series, which sequentially calculates attention from the lower level to the upper level. Experiments on four long time series datasets demonstrate superior classification results with improved efficiency compared to baseline methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_04882 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition Feng, Aosong Chen, Jialin Garza, Juan Berry, Brooklyn Salazar, Francisco Gao, Yifeng Ying, Rex Tassiulas, Leandros Machine Learning The high-resolution time series classification problem is essential due to the increasing availability of detailed temporal data in various domains. To tackle this challenge effectively, it is imperative that the state-of-the-art attention model is scalable to accommodate the growing sequence lengths typically encountered in high-resolution time series data, while also demonstrating robustness in handling the inherent noise prevalent in such datasets. To address this, we propose to hierarchically encode the long time series into multiple levels based on the interaction ranges. By capturing relationships at different levels, we can build more robust, expressive, and efficient models that are capable of capturing both short-term fluctuations and long-term trends in the data. We then propose a new time series transformer backbone (KronTime) by introducing Kronecker-decomposed attention to process such multi-level time series, which sequentially calculates attention from the lower level to the upper level. Experiments on four long time series datasets demonstrate superior classification results with improved efficiency compared to baseline methods. |
| title | Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.04882 |