Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.04600 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908463410446336 |
|---|---|
| author | Liu, Zhipeng Duan, Peibo Wang, Binwu Tang, Xuan Chu, Qi Zhang, Changsheng Huang, Yongsheng Zhang, Bin |
| author_facet | Liu, Zhipeng Duan, Peibo Wang, Binwu Tang, Xuan Chu, Qi Zhang, Changsheng Huang, Yongsheng Zhang, Bin |
| contents | Real-world time series typically exhibit complex temporal variations, making the time series classification task notably challenging. Recent advancements have demonstrated the potential of multi-scale analysis approaches, which provide an effective solution for capturing these complex temporal patterns. However, existing multi-scale analysis-based time series prediction methods fail to eliminate redundant scale-shared features across multi-scale time series, resulting in the model over- or under-focusing on scale-shared features. To address this issue, we propose a novel end-to-end Disentangled Multi-Scale framework for Time Series classification (DisMS-TS). The core idea of DisMS-TS is to eliminate redundant shared features in multi-scale time series, thereby improving prediction performance. Specifically, we propose a temporal disentanglement module to capture scale-shared and scale-specific temporal representations, respectively. Subsequently, to effectively learn both scale-shared and scale-specific temporal representations, we introduce two regularization terms that ensure the consistency of scale-shared representations and the disparity of scale-specific representations across all temporal scales. Extensive experiments conducted on multiple datasets validate the superiority of DisMS-TS over its competitive baselines, with the accuracy improvement up to 9.71%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_04600 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification Liu, Zhipeng Duan, Peibo Wang, Binwu Tang, Xuan Chu, Qi Zhang, Changsheng Huang, Yongsheng Zhang, Bin Artificial Intelligence Real-world time series typically exhibit complex temporal variations, making the time series classification task notably challenging. Recent advancements have demonstrated the potential of multi-scale analysis approaches, which provide an effective solution for capturing these complex temporal patterns. However, existing multi-scale analysis-based time series prediction methods fail to eliminate redundant scale-shared features across multi-scale time series, resulting in the model over- or under-focusing on scale-shared features. To address this issue, we propose a novel end-to-end Disentangled Multi-Scale framework for Time Series classification (DisMS-TS). The core idea of DisMS-TS is to eliminate redundant shared features in multi-scale time series, thereby improving prediction performance. Specifically, we propose a temporal disentanglement module to capture scale-shared and scale-specific temporal representations, respectively. Subsequently, to effectively learn both scale-shared and scale-specific temporal representations, we introduce two regularization terms that ensure the consistency of scale-shared representations and the disparity of scale-specific representations across all temporal scales. Extensive experiments conducted on multiple datasets validate the superiority of DisMS-TS over its competitive baselines, with the accuracy improvement up to 9.71%. |
| title | DisMS-TS: Eliminating Redundant Multi-Scale Features for Time Series Classification |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2507.04600 |