| 题名 | A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis |
| 作者 | |
| 发表日期 | 2024 |
| 会议名称 | 50th International Conference on Very Large Data Bases, VLDB 2024 |
| 会议录名称 | Proceedings of the VLDB Endowment
 |
| 卷号 | 17 |
| 期号 | 7 |
| 页码 | 1723-1736 |
| 会议日期 | 2024-08-24——2024-08-29 |
| 会议地点 | Guangzhou |
| 摘要 | Time series data, including univariate and multivariate ones, are characterized by unique composition and complex multi-scale temporal variations. They often require special consideration of decomposition and multi-scale modeling to analyze. Existing deep learning methods on this best ft to univariate time series only, and have not sufciently considered sub-series modeling and decomposition completeness. To address these challenges, we propose MSD-Mixer, a Multi-Scale Decomposition MLP-Mixer, which learns to explicitly decompose and represent the input time series in its diferent layers. To handle the multi-scale temporal patterns and multivariate dependencies, we propose a novel temporal patching approach to model the time series as multi-scale patches, and employ MLPs to capture intra- and inter-patch variations and channel-wise correlations. In addition, we propose a novel loss function to constrain both the mean and the autocorrelation of the decomposition residual for better decomposition completeness. Through extensive experiments on various real-world datasets for fve common time series analysis tasks, we demonstrate that MSD-Mixer consistently and signifcantly outperforms other state-of-the-art algorithms with better efciency. |
| DOI | 10.14778/3654621.3654637 |
| URL | 查看来源 |
| 语种 | 英语English |
| Scopus入藏号 | 2-s2.0-85195662710 |
| 引用统计 | |
| 文献类型 | 会议论文 |
| 条目标识符 | https://repository.uic.edu.cn/handle/39GCC9TT/13682 |
| 专题 | 北师香港浸会大学 |
| 作者单位 | 1.Department of Computer Science and Engineering,The Hong Kong University of Science and Technology,Hong Kong 2.Guangdong Provincial Key Laboratory IRADS and Department of Computer Science,BNU-HKBU United International College,China 3.Guangdong Enterprise Key Laboratory for Urban Sensing,Monitoring and Early Warning Guangzhou Urban Planning and Design Survey Research Institute,China |
| 推荐引用方式 GB/T 7714 | Zhong，Shuhan,Song，Sizhe,Zhuo，Weipenget al. A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis[C], 2024: 1723-1736. |
| 条目包含的文件 | 条目无相关文件。 | |||||
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
学校主页 
图书馆
修改评论