Skip to content
Open access

MMCont-Net: toward full-scale context modeling for irregular series forecasting

Nov 2026 · Journal of Supercomputing · Vol 82 · 0 citations · 50 references

Abstract

Forecasting irregularly sampled multivariate time series (IMTS) remains a fundamental challenge in contemporary time series analysis, owing to the inherent non-uniformity of sampling and pronounced inter-variable asynchrony. While recent advances in context learning achieves remarkable performance, microscopic signal distortion and macroscopic spatial isolation issues still limit the effectiveness of irregular series forecasting. In this paper, we propose MMCont-Net (Micro–Macro Context Modeling Network), a novel framework that pioneers complementary full-scale context modeling. It progressively integrates micro-level signal perception and macro-level spatial interaction, and achieves stable superior performance across diverse irregular forecasting scenarios. Extensive experiments on multiple benchmark datasets, including PhysioNet, Human Activity, USHCN, and MIMIC-III, demonstrate that MMCont-Net consistently achieves lower forecasting errors while maintaining superior computational efficiency and robustness, demonstrating the importance of the proposed full-scale context modeling paradigm.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.