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

ICLR 2026 Conference Submission14778 Authors

Keywords: Irregular Multivariate Time Series, Time Series Forecasting, Multi-Scale Learning

TL;DR: We propose a recursive multi-scale modeling approach that preserves sampling patterns for irregular multivariate time series forecasting task, which boosts performance of existing models while maintaining good efficiency.

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 **Re**cursive multi-scale modeling approach for **I**rregular **M**ultivariate **T**ime **S**eries 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 29.1\% in the forecasting task across different models and real-world datasets.
Our code is available at [https://anonymous.4open.science/r/ReIMTS-CA7B/](https://anonymous.4open.science/r/ReIMTS-CA7B/).

Primary Area: learning on time series and dynamical systems

Submission Number: 14778