Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting

TL;DR

ReIMTS introduces a recursive multi-scale approach for irregular multivariate time series forecasting that preserves original timestamps and captures dependencies across multiple time scales, significantly improving accuracy.

Contribution

The paper proposes ReIMTS, a novel recursive multi-scale modeling method that avoids resampling and maintains timestamp integrity for better dependency learning in IMTS forecasting.

Findings

Achieves an average of 27.1% performance improvement across datasets.

Effectively captures global-to-local dependencies without resampling.

Demonstrates robustness across different models and real-world data.

Abstract

Irregular Multivariate Time Series (IMTS) are characterized by uneven intervals between consecutive timestamps, which carry sampling pattern information valuable and informative for learning temporal and variable dependencies. In addition, IMTS often exhibit diverse dependencies across multiple time scales. However, many existing multi-scale IMTS methods use resampling to obtain the coarse series, which can alter the original timestamps and disrupt the sampling pattern information. To address the challenge, we propose ReIMTS, a Recursive multi-scale modeling approach for Irregular Multivariate Time Series forecasting. Instead of resampling, ReIMTS keeps timestamps unchanged and recursively splits each sample into subsamples with progressively shorter time periods. Based on the original sampling timestamps in these long-to-short subsamples, an irregularity-aware representation fusion mechanism is proposed to capture global-to-local dependencies for accurate forecasting. Extensive experiments demonstrate an average performance improvement of 27.1\% in the forecasting task across different models and real-world datasets. Our code is available at https://github.com/Ladbaby/PyOmniTS.