{"ID":2861825,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.00461","arxiv_id":"2510.00461","title":"TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.00461","url_pdf":"https://arxiv.org/pdf/2510.00461v2","authors":"[\"Mingyuan Xia\",\"Chunxu Zhang\",\"Zijian Zhang\",\"Hao Miao\",\"Qidong Liu\",\"Yuanshao Zhu\",\"Bo Yang\"]","published":"2025-10-01T03:28:49Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":608844,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2861825,"paper_url":"https://arxiv.org/abs/2510.00461","paper_title":"TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting","repo_url":"https://github.com/showmeon/TimeEmb","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}