Mixing It Up: Exploring Mixer Networks for Irregular Multivariate Time Series Forecasting
This addresses forecasting challenges in domains like healthcare and climate research where data is irregular and missing, offering a specialized solution for an emerging field.
The paper tackled forecasting irregular multivariate time series (IMTS) by introducing IMTS-Mixer, a novel architecture that transforms IMTS into fixed-size matrices for use with mixer modules, achieving new state-of-the-art accuracy and improved computational efficiency on four real-world datasets.
Forecasting Irregular Multivariate Time Series (IMTS) has recently emerged as a distinct research field, necessitating specialized models to address its unique challenges. While most forecasting literature assumes regularly spaced observations without missing values, many real-world datasets - particularly in healthcare, climate research, and biomechanics - violate these assumptions. Time Series (TS)-mixer models have achieved remarkable success in regular multivariate time series forecasting. However, they remain unexplored for IMTS due to their requirement for complete and evenly spaced observations. To bridge this gap, we introduce IMTS-Mixer, a novel forecasting architecture designed specifically for IMTS. Our approach retains the core principles of TS mixer models while introducing innovative methods to transform IMTS into fixed-size matrix representations, enabling their seamless integration with mixer modules. We evaluate IMTS-Mixer on a benchmark of four real-world datasets from various domains. Our results demonstrate that IMTS-Mixer establishes a new state-of-the-art in forecasting accuracy while also improving computational efficiency.