WaveTuner: Comprehensive Wavelet Subband Tuning for Time Series Forecasting
By: Yubo Wang , Hui He , Chaoxi Niu and more
Potential Business Impact:
Improves predictions by analyzing all time-series details.
Due to the inherent complexity, temporal patterns in real-world time series often evolve across multiple intertwined scales, including long-term periodicity, short-term fluctuations, and abrupt regime shifts. While existing literature has designed many sophisticated decomposition approaches based on the time or frequency domain to partition trend-seasonality components and high-low frequency components, an alternative line of approaches based on the wavelet domain has been proposed to provide a unified multi-resolution representation with precise time-frequency localization. However, most wavelet-based methods suffer from a persistent bias toward recursively decomposing only low-frequency components, severely underutilizing subtle yet informative high-frequency components that are pivotal for precise time series forecasting. To address this problem, we propose WaveTuner, a Wavelet decomposition framework empowered by full-spectrum subband Tuning for time series forecasting. Concretely, WaveTuner comprises two key modules: (i) Adaptive Wavelet Refinement module, that transforms time series into time-frequency coefficients, utilizes an adaptive router to dynamically assign subband weights, and generates subband-specific embeddings to support refinement; and (ii) Multi-Branch Specialization module, that employs multiple functional branches, each instantiated as a flexible Kolmogorov-Arnold Network (KAN) with a distinct functional order to model a specific spectral subband. Equipped with these modules, WaveTuner comprehensively tunes global trends and local variations within a unified time-frequency framework. Extensive experiments on eight real-world datasets demonstrate WaveTuner achieves state-of-the-art forecasting performance in time series forecasting.
Similar Papers
Wavelet Mixture of Experts for Time Series Forecasting
Machine Learning (CS)
Predicts future events more accurately with less data.
Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting
Machine Learning (CS)
Predicts future events better by spotting changes.
Hi-WaveTST: A Hybrid High-Frequency Wavelet-Transformer for Time-Series Classification
Signal Processing
Finds hidden patterns in time data for better predictions.