TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914104315215872 |
|---|---|
| author | Xia, Mingyuan Zhang, Chunxu Zhang, Zijian Miao, Hao Liu, Qidong Zhu, Yuanshao Yang, Bo |
| author_facet | Xia, Mingyuan Zhang, Chunxu Zhang, Zijian Miao, Hao Liu, Qidong Zhu, Yuanshao Yang, Bo |
| contents | Temporal non-stationarity, the phenomenon that time series distributions change over time, poses fundamental challenges to reliable time series forecasting. Intuitively, the complex time series can be decomposed into two factors, \ie time-invariant and time-varying components, which indicate static and dynamic patterns, respectively. Nonetheless, existing methods often conflate the time-varying and time-invariant components, and jointly learn the combined long-term patterns and short-term fluctuations, leading to suboptimal performance facing distribution shifts. To address this issue, we initiatively propose a lightweight static-dynamic decomposition framework, TimeEmb, for time series forecasting. TimeEmb innovatively separates time series into two complementary components: (1) time-invariant component, captured by a novel global embedding module that learns persistent representations across time series, and (2) time-varying component, processed by an efficient frequency-domain filtering mechanism inspired by full-spectrum analysis in signal processing. Experiments on real-world datasets demonstrate that TimeEmb outperforms state-of-the-art baselines and requires fewer computational resources. We conduct comprehensive quantitative and qualitative analyses to verify the efficacy of static-dynamic disentanglement. This lightweight framework can also improve existing time-series forecasting methods with simple integration. To ease reproducibility, the code is available at https://github.com/showmeon/TimeEmb. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00461 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting Xia, Mingyuan Zhang, Chunxu Zhang, Zijian Miao, Hao Liu, Qidong Zhu, Yuanshao Yang, Bo Machine Learning Artificial Intelligence Temporal non-stationarity, the phenomenon that time series distributions change over time, poses fundamental challenges to reliable time series forecasting. Intuitively, the complex time series can be decomposed into two factors, \ie time-invariant and time-varying components, which indicate static and dynamic patterns, respectively. Nonetheless, existing methods often conflate the time-varying and time-invariant components, and jointly learn the combined long-term patterns and short-term fluctuations, leading to suboptimal performance facing distribution shifts. To address this issue, we initiatively propose a lightweight static-dynamic decomposition framework, TimeEmb, for time series forecasting. TimeEmb innovatively separates time series into two complementary components: (1) time-invariant component, captured by a novel global embedding module that learns persistent representations across time series, and (2) time-varying component, processed by an efficient frequency-domain filtering mechanism inspired by full-spectrum analysis in signal processing. Experiments on real-world datasets demonstrate that TimeEmb outperforms state-of-the-art baselines and requires fewer computational resources. We conduct comprehensive quantitative and qualitative analyses to verify the efficacy of static-dynamic disentanglement. This lightweight framework can also improve existing time-series forecasting methods with simple integration. To ease reproducibility, the code is available at https://github.com/showmeon/TimeEmb. |
| title | TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2510.00461 |