FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency Decomposition
Time series forecasting is essential in a wide range of real world applications. Recently, frequency-domain methods have attracted increasing interest for their ability to capture global dependencies. However, when applied to non-stationary time series, these methods encounter the $\textit{spectral entanglement}$ and the computational burden of complex-valued learning. The $\textit{spectral entanglement}$ refers to the overlap of trends, periodicities, and noise across the spectrum due to $\textit{spectral leakage}$ and the presence of non-stationarity. However, existing decompositions are not suited to resolving spectral entanglement. To address this, we propose the Frequency Decomposition Network (FreDN), which introduces a learnable Frequency Disentangler module to separate trend and periodic components directly in the frequency domain. Furthermore, we propose a theoretically supported ReIm Block to reduce the complexity of complex-valued operations while maintaining performance. We also re-examine the frequency-domain loss function and provide new theoretical insights into its effectiveness. Extensive experiments on seven long-term forecasting benchmarks demonstrate that FreDN outperforms state-of-the-art methods by up to 10\%. Furthermore, compared with standard complex-valued architectures, our real-imaginary shared-parameter design reduces the parameter count and computational cost by at least 50\%.
Code (0)
등록된 구현이 없습니다.
Tasks
Time Series ForecastingSimilar Papers 제목 키워드 기반
FredNormer: Frequency Domain Normalization for Non-stationary Time Series Forecasting
Recent normalization-based methods have shown great success in tackling the distribution shift issue, facilitating non-stationary time series forecasting. Since these methods operate in the time domain, they may fail to …
Time SeriesTime Series ForecastingGenerative Time Series Forecasting with Diffusion, Denoise, and Disentanglement
Time series forecasting has been a widely explored task of great importance in many applications. However, it is common that real-world time series data are recorded in a short time period, which results in a big gap bet…
DenoisingDisentanglementTime SeriesTime Series Analysis+1TimeEmb: A Lightweight Static-Dynamic Disentanglement Framework for Time Series Forecasting
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…
Time Series ForecastingDual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
Real-world time series are governed by both recurring structures, such as trends and seasonality, and infrequent yet critical variations, such as abrupt shifts and rare events. However, existing methods often lack an exp…
Time Series ForecastingDisentangling Long-Short Term State Under Unknown Interventions for Online Time Series Forecasting
Current methods for time series forecasting struggle in the online scenario, since it is difficult to preserve long-term dependency while adapting short-term changes when data are arriving sequentially. Although some rec…
DisentanglementTime SeriesTime Series Forecasting