GLAIM: Learning Global and Local Adaptive Inter-Variable Dependency for Multivariate Time Series Imputation

2026-08-03

AI Summary

This work addresses the challenge of accurately modeling variable dependencies in multivariate time series under missing observations, where existing methods often struggle to balance the stability of global dependencies with the adaptability of local ones. To overcome this limitation, we propose GLAIM, a novel framework that learns robust global dependencies through complementary temporal representations and introduces a sample-conditioned dependency refiner that adaptively adjusts local structures based on available observations at each time step. By synergistically integrating global and local modeling strengths, GLAIM effectively suppresses error propagation induced by missing data while enabling end-to-end imputation. Extensive experiments demonstrate that GLAIM achieves state-of-the-art performance across nine real-world datasets under both random and block-wise missing patterns and exhibits strong robustness to varying missing rates.

Abstract

Multivariate time series imputation is fundamental to downstream analysis, yet modeling inter-variable dependencies with incomplete observations remains challenging. Existing methods learn global dependencies across samples or dynamic local dependencies per sample. Global dependencies are stable but adapt poorly to sample variations and temporal non-stationarity, whereas local dependencies are adaptive yet unreliable when observations are insufficient, causing erroneous information propagation. To address these limitations, we propose GLAIM, a Global-Local Adaptive Inter-variable Dependency Modeling framework for multivariate time series imputation. GLAIM comprises two complementary components. The Stable Global Dependency Constructor derives robust global inter-variable dependencies from complementary temporal representations, providing a stable backbone less affected by sample-specific missingness and noise. The Sample-Conditioned Dependency Refiner adapts this backbone to each sample and time step using its temporal state and available observations, enabling reliable local refinement under incomplete observations. Extensive experiments on nine real-world datasets demonstrate that GLAIM achieves state-of-the-art performance under random and block missingness, remains robust to missing-rate shifts, and benefits from its complementary global and local components. Code is available at https://github.com/LuRenjias/GLAIM.

Problem

• multivariate time series imputation
• inter-variable dependency
• incomplete observations
• global dependency
• local dependency

Innovation

• multivariate time series imputation
• global-local dependency modeling
• adaptive inter-variable dependency
• missing data imputation
• temporal representation learning