Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness

ICLR 2026 Conference Submission16227 Authors

Keywords: Time Series Forecasting, Channel Dependence, Asynchronous Sampling, Missing Blocks

TL;DR: To address a trio of real-world challenges involving inter-channel dependencies, asynchronous sampling, and test-time missing blocks, we introduce ChannelTokenFormer that achieves robust performance without requiring explicit temporal alignment.

Abstract: Real-world time series data are inherently multivariate, often exhibiting complex inter-channel dependencies. Each channel is typically sampled at its own period and is prone to missing values due to various practical and operational constraints. These characteristics pose three fundamental challenges involving channel dependency, sampling asynchrony, and missingness, all of which must be addressed simultaneously to enable robust and reliable forecasting in practical settings. However, existing architectures typically address only parts of these challenges in isolation and still rely on simplifying assumptions, leaving unresolved the combined challenges of asynchronous channel sampling, test-time missing blocks, and intricate inter-channel dependencies. To bridge this gap, we propose ChannelTokenFormer, a Transformer-based forecasting framework with a flexible architecture designed to explicitly capture cross-channel interactions, accommodate channel-wise asynchronous sampling, and effectively handle missing values. Extensive experiments on public benchmark datasets reflecting practical settings, along with one private real-world industrial dataset, demonstrate the superior robustness and accuracy of ChannelTokenFormer under challenging real-world conditions.

Primary Area: learning on time series and dynamical systems

Submission Number: 16227