WindowMixer: Intra-Window and Inter-Window Modeling for Time Series Forecasting

TL;DR

WindowMixer is a novel all-MLP model that captures complex temporal patterns in time series data by decomposing into trend and seasonal components and modeling intra- and inter-window relationships, leading to improved forecasting accuracy.

Contribution

The paper introduces WindowMixer, a new all-MLP based approach that models intra- and inter-window relationships for enhanced time series forecasting.

Findings

Outperforms existing methods in long-term forecasting

Effective in handling noise and missing data

Captures long-range dependencies accurately

Abstract

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.