T1: One-to-One Channel-Head Binding for Multivariate Time-Series Imputation

ICLR 2026 Conference Submission17899 Authors

Keywords: Time Series, Imputation

TL;DR: T1 is a CNN-Transformer hybrid that binds channels to attention heads for robust time series imputation, achieving 46% better performance than existing methods, especially under extreme missingness.

Abstract: Imputing missing values in multivariate time series remains challenging, especially under diverse missing patterns and heavy missingness. Existing methods suffer from suboptimal performance as corrupted temporal features hinder effective cross-variable information transfer, amplifying reconstruction errors. Robust imputation requires both extracting temporal patterns from sparse observations within each variable and selectively transferring information across variables—yet current approaches excel at one while compromising the other. We introduce T1 (Time series imputation with 1-to-1 channel-head binding), a CNN-Transformer hybrid architecture that achieves robust imputation through Channel-Head Binding—a mechanism creating one-to-one correspondence between CNN channels and attention heads. This design enables selective information transfer: when missingness corrupts certain temporal patterns, their corresponding attention pathways adaptively down-weight based on remaining observable patterns while preserving reliable cross-variable connections through unaffected channels. Experiments on 11 benchmark datasets demonstrate that T1 achieves state-of-the-art performance, reducing MSE by 46% on average compared to the second-best baseline, with particularly strong gains under extreme sparsity (70% missing ratio). The model generalizes to unseen missing patterns without retraining and uses a single hyperparameter configuration across all datasets.

Primary Area: learning on time series and dynamical systems

Submission Number: 17899