Revitalizing Multivariate Time Series Forecasting: Learnable Decomposition with Inter-Series Dependencies and Intra-Series Variations Modeling
This work addresses the problem of accurate forecasting for multivariate time series in domains like finance or weather, offering a novel method that can be integrated into existing approaches for significant gains.
The paper tackles multivariate time series forecasting by introducing a learnable decomposition strategy and a dual attention module to model inter-series dependencies and intra-series variations, achieving performance improvements of 11.87% to 48.56% MSE error reduction compared to state-of-the-art methods.
Predicting multivariate time series is crucial, demanding precise modeling of intricate patterns, including inter-series dependencies and intra-series variations. Distinctive trend characteristics in each time series pose challenges, and existing methods, relying on basic moving average kernels, may struggle with the non-linear structure and complex trends in real-world data. Given that, we introduce a learnable decomposition strategy to capture dynamic trend information more reasonably. Additionally, we propose a dual attention module tailored to capture inter-series dependencies and intra-series variations simultaneously for better time series forecasting, which is implemented by channel-wise self-attention and autoregressive self-attention. To evaluate the effectiveness of our method, we conducted experiments across eight open-source datasets and compared it with the state-of-the-art methods. Through the comparison results, our Leddam (LEarnable Decomposition and Dual Attention Module) not only demonstrates significant advancements in predictive performance, but also the proposed decomposition strategy can be plugged into other methods with a large performance-boosting, from 11.87% to 48.56% MSE error degradation.