Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2504.02013 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909563243986944 |
|---|---|
| author | Xiong, Sijie Liu, Shuqing Tang, Cheng Okubo, Fumiya Xiong, Haoling Shimada, Atsushi |
| author_facet | Xiong, Sijie Liu, Shuqing Tang, Cheng Okubo, Fumiya Xiong, Haoling Shimada, Atsushi |
| contents | "This work has been submitted to the lEEE for possible publication. Copyright may be transferred without noticeafter which this version may no longer be accessible." Time series modeling serves as the cornerstone of real-world applications, such as weather forecasting and transportation management. Recently, Mamba has become a promising model that combines near-linear computational complexity with high prediction accuracy in time series modeling, while facing challenges such as insufficient modeling of nonlinear dependencies in attention and restricted receptive fields caused by convolutions. To overcome these limitations, this paper introduces an innovative framework, Attention Mamba, featuring a novel Adaptive Pooling block that accelerates attention computation and incorporates global information, effectively overcoming the constraints of limited receptive fields. Furthermore, Attention Mamba integrates a bidirectional Mamba block, efficiently capturing long-short features and transforming inputs into the Value representations for attention mechanisms. Extensive experiments conducted on diverse datasets underscore the effectiveness of Attention Mamba in extracting nonlinear dependencies and enhancing receptive fields, establishing superior performance among leading counterparts. Our codes will be available on GitHub. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02013 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Attention Mamba: Time Series Modeling with Adaptive Pooling Acceleration and Receptive Field Enhancements Xiong, Sijie Liu, Shuqing Tang, Cheng Okubo, Fumiya Xiong, Haoling Shimada, Atsushi Machine Learning "This work has been submitted to the lEEE for possible publication. Copyright may be transferred without noticeafter which this version may no longer be accessible." Time series modeling serves as the cornerstone of real-world applications, such as weather forecasting and transportation management. Recently, Mamba has become a promising model that combines near-linear computational complexity with high prediction accuracy in time series modeling, while facing challenges such as insufficient modeling of nonlinear dependencies in attention and restricted receptive fields caused by convolutions. To overcome these limitations, this paper introduces an innovative framework, Attention Mamba, featuring a novel Adaptive Pooling block that accelerates attention computation and incorporates global information, effectively overcoming the constraints of limited receptive fields. Furthermore, Attention Mamba integrates a bidirectional Mamba block, efficiently capturing long-short features and transforming inputs into the Value representations for attention mechanisms. Extensive experiments conducted on diverse datasets underscore the effectiveness of Attention Mamba in extracting nonlinear dependencies and enhancing receptive fields, establishing superior performance among leading counterparts. Our codes will be available on GitHub. |
| title | Attention Mamba: Time Series Modeling with Adaptive Pooling Acceleration and Receptive Field Enhancements |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.02013 |