WindowMixer: Intra-Window and Inter-Window Modeling for Time Series Forecasting
This addresses forecasting problems in domains like economics and weather, but it appears incremental as it builds on window-based and decomposition techniques.
The paper tackles the challenge of accurate time series forecasting in noisy real-world data by introducing WindowMixer, an all-MLP model that decomposes series into trend and seasonal components and uses intra- and inter-window modeling, which consistently outperforms existing methods in long-term and short-term tasks.
Time series forecasting (TSF) is crucial in fields like economic forecasting, weather prediction, traffic flow analysis, and public health surveillance. Real-world time series data often include noise, outliers, and missing values, making accurate forecasting challenging. Traditional methods model point-to-point relationships, which limits their ability to capture complex temporal patterns and increases their susceptibility to noise.To address these issues, we introduce the WindowMixer model, built on an all-MLP framework. WindowMixer leverages the continuous nature of time series by examining temporal variations from a window-based perspective. It decomposes time series into trend and seasonal components, handling them individually. For trends, a fully connected (FC) layer makes predictions. For seasonal components, time windows are projected to produce window tokens, processed by Intra-Window-Mixer and Inter-Window-Mixer modules. The Intra-Window-Mixer models relationships within each window, while the Inter-Window-Mixer models relationships between windows. This approach captures intricate patterns and long-range dependencies in the data.Experiments show WindowMixer consistently outperforms existing methods in both long-term and short-term forecasting tasks.