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

Mingyuan Xia, Chunxu Zhang, Zijian Zhang, Hao Miao, Qidong Liu, Yuanshao Zhu, Bo Yang

Jilin University· Hong Kong Polytechnic University· Xi'an Jiaotong University· City University of Hong Kong

Time series forecasting Frequency domain analysis Disentangled representation learning

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, 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:

time-invariant component, captured by a novel global embedding module that learns persistent representations across time series, and
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.