TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting

Yuanshao Zhu (City University of Hong Kong) · Zijian Zhang (Harbin Institute of Technology) · Mingyuan Xia (Jilin University) · Chunxu Zhang (Jilin University) · Hao Miao (Hong Kong Polytechnic University) · Qidong Liu (Xi'an Jiaotong University) · Bo Yang (Jilin University)
computational resourcesfrequency-domain filteringfull-spectrum analysisglobal embedding modulepersistent representationsqualitative analysisquantitative analysisreproducibilitysignal processingstate-of-the-art baselinesstatic-dynamic decompositionstatic-dynamic disentanglementtemporal non-stationaritytime series forecastingtime-invariant componenttime-varying component

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, i.e., 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, our code is available at https://github.com/showmeon/TimeEmb.