Stationarity Exploration for Multivariate Time Series Forecasting
By: Hao Liu , Chun Yang , Zhang xiaoxing and more
Potential Business Impact:
Predicts future events by understanding signal patterns.
Deep learning-based time series forecasting has found widespread applications. Recently, converting time series data into the frequency domain for forecasting has become popular for accurately exploring periodic patterns. However, existing methods often cannot effectively explore stationary information from complex intertwined frequency components. In this paper, we propose a simple yet effective Amplitude-Phase Reconstruct Network (APRNet) that models the inter-relationships of amplitude and phase, which prevents the amplitude and phase from being constrained by different physical quantities, thereby decoupling the distinct characteristics of signals for capturing stationary information. Specifically, we represent the multivariate time series input across sequence and channel dimensions, highlighting the correlation between amplitude and phase at multiple interaction frequencies. We propose a novel Kolmogorov-Arnold-Network-based Local Correlation (KLC) module to adaptively fit local functions using univariate functions, enabling more flexible characterization of stationary features across different amplitudes and phases. This significantly enhances the model's capability to capture time-varying patterns. Extensive experiments demonstrate the superiority of our APRNet against the state-of-the-arts (SOTAs).
Similar Papers
Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism
Machine Learning (CS)
Predicts future events better when things change.
AR-KAN: Autoregressive-Weight-Enhanced Kolmogorov-Arnold Network for Time Series Forecasting
Machine Learning (CS)
Predicts future events better than other computer brains.
Frequency-Constrained Learning for Long-Term Forecasting
Machine Learning (CS)
Predicts future events by understanding repeating patterns.