cs.LGFeb 24, 2026

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

Authors: Dongik Park, Hyunwoo Ryu, Suahn Bae, Keondo Park, Hyung-Sin Kim

Organizations: Graduate School of Data Science, Seoul National University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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 consistent hyperparameter configuration across all datasets. The code is available at https://github.com/Oppenheimerdinger/T1.

Figures & tables

Figure 1: T1 introduces CNN-Transformer hybrid architecture that effectively processes information by strategically assigning CNN or attention to the temporal, feature, and variable dimensions using depthwise (DW) and pointwise (PW) convolutions. In our novel mechanism, CHead Attention , each channel encoded by shared CNN is directly aligned with a single attention head. It facilitates cross-variable information exchange, ensuring that interactions occur only between semantically similar temporal features.
Figure 2: An overview of the T1 architecture. (a) The Mask-Aware Embedding module encodes the input series and its observation mask into a latent representation using 1D convolutions. (b) The Temporal Convolutional QKV Projection block employs Depthwise Convolutions to extract consistent temporal patterns for each channel. The kernel weights are shared across variables, resulting in semantically-aligned Query, Key, and Value embedding. (c) Our proposed Channel-Head Attention (CHead Attention) is applied across the variable axis to selectively transfer information. Each head is bound to a single channel, enabling feature-specific fusion between semantically-aligned patterns. (d) The Reconstruction Upsampler restores the original temporal resolution of the series via a parameter-free 1D PixelShuffle operation followed by a final pointwise convolution.
Figure 3: Representation analysis of T1’s attention mechanism. (a) Layer-wise attention weights from other variables to target variable under varying missing ratios (entire ETTh1 test set). Attention weights decrease with increasing missing ratio, with shallow layers showing more pronounced degradation. (b) Head-specific attention patterns of clean signal and under various missing patterns (peak vs non-peak and high vs low variance, 30% each), showing top-20 heads sorted by clean attention weights.
ComponentAlternativeETTh1ETTh2ETTm1ETTm2WeatherECLAvgΔ\Delta (%) ↓\downarrow
T1 (Ours)0.0490.0360.0220.0170.0290.0430.033-
Cross-variable ComponentConv0.0560.0400.0240.0200.0290.0520.037+ 12.91
w/o0.0950.0640.0400.0290.0310.0480.051+ 56.16
Channel-Head Binding32 Chns0.0610.0400.0300.0200.0300.0440.037+ 14.57
16 Chns0.0660.0410.0280.0200.0300.0450.038+ 16.86
8 Chns0.0550.0380.0250.0190.0300.0440.035+ 7.45
Table 5: Comprehensive ablation study on model components (MSE). Each row shows the performance when replacing only the specified component from our full model. The last column shows the percentage increase in error relative to our full model.
Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

TypeDatasetVariablesTrainValidTestFrequencyMissing Ratio
CompleteETTh1,ETTh278,5452,7852,785Hourly-
ETTm1,ETTm2734,46511,42511,42515min-
Electricity32118,3462,6215,424Hourly-
Weather2136,8205,26010,52110min-
Illness760987175Weekly-
Exchange85,2457491,499Daily-
Appendix
Table 6: Dataset descriptions.
Figure 4: Hyperparameter Sensitivity analysis with respect to the number of heads, FFN ratio, and kernel size.
Figure 5: Extended attention analysis under varying missingness patterns (expansion of Figure 3(b)). (a) Left: Example time series (var4 from ETTh1) with four masking strategies targeting peak, non-peak, high-variance, and low-variance regions. Right: Mean attention weights to the target variable across 10 heads and 5 conditions. (b) Full 7 ×\times 7 inter-variable attention maps for the top-10 heads (sorted by clean attention weights). Magenta lines indicate the target variable (var4). (c) Attention difference from the clean condition, showing how each head adapts its attention distribution in response to different missing patterns. Red indicates increased attention; blue indicates decreased attention.
Category# VarsMissing RateExamples
Vital Signs130.19 – 0.94HR (0.19), Urine (0.37), Temp (0.67), NISysABP (0.94)
Lab Measurements230.51 – 1.00Mg (0.51), PaO2 (0.90), Cholesterol (1.00)
Appendix
Table 15: PhysioNet2012 variable-level missing rate distribution by category.
Figure 6: Visualization of imputation results on PhysioNet2012 for HR.
Figure 7: Visualization of imputation results on PhysioNet2012 for Temp.
Figure 8: Visualization of imputation results on PhysioNet2012 for PaO2.
More in this topic

Time Series Imputation

Time series imputation reconstructs missing observations in sequential data using temporal, cross-variable, and domain-specific patterns.

See all 58 papers

Explore similar work

CardsList
Jul 8, 2026

ALER-TI: Aligned Latent Embedding Retrieval for Time Series Imputation

Deep learning has significantly advanced time series imputation, yet most existing architectures primarily rely on localized temporal context within the corrupted input sequence. This reliance can be limiting in real-world scenarios, where time series often exhibit non-stationary dynamics, weak temporal correlations, and infrequent patterns that are difficult to reconstruct from nearby observations alone. In this paper, we propose ALER-TI, Aligned Latent Embedding Retrieval for Time Series Imputation, a retrieval-augmented framework that explicitly leverages historical patterns to supplement degraded local context for more reliable missing-value reconstruction. The core of ALER-TI is Latent Embedding Alignment (LEA), which mitigates the representation mismatch between corrupted queries and complete historical candidates. By applying post-hoc masking in the latent space, LEA aligns candidates with the query's missingness pattern while allowing historical embeddings to be pre-computed and cached for efficient retrieval. ALER-TI is model-agnostic and can be integrated with various imputation backbones through a lightweight adaptation module. Extensive experiments on six real-world datasets under different missing rates demonstrate that ALER-TI consistently improves strong baseline models and enhances robustness across diverse imputation settings.

Xuan-Thong Truong, Trung-Kien Le, Tung Kieu +2

School of Computer Science, Hanoi University of Science and Technology, Hanoi, Vietnam · Department of Computer Science, Aalborg University, Aalborg, Denmark

Time Series ImputationRepresentation Alignment
AskPDF
Dec 17, 2025

FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation

Multivariate time series imputation is fundamental in applications such as healthcare, traffic forecasting, and biological modeling, where sensor failures and irregular sampling lead to pervasive missing values. Existing Transformer- and diffusion-based imputers achieve strong performance, but they often rely mainly on time-domain modeling and lack adaptive spectral bias for recovering structured temporal gaps. We propose FADTI, a Fourier- and attention-driven diffusion framework for multivariate time series imputation. FADTI introduces a Fourier Bias Projection (FBP) module that injects learnable frequency-aware bias into intermediate hidden states during denoising. It projects intermediate hidden states onto Fourier bases, avoiding direct spectral estimation from masked or zero-filled inputs. With DFT, STFT, and FSST instantiations, FBP captures global periodicity, localized time--frequency variations, and non-stationary oscillatory patterns. By coupling FBP with self-attention and gated convolution, FADTI integrates frequency-domain guidance, temporal dependency modeling, and probabilistic denoising in a unified framework. Experiments on multiple benchmarks, including a new biological imputation benchmark, show that FADTI improves accuracy, uncertainty estimation, and sampling efficiency, especially under high missing rates and structured missing patterns. Code is available at https://github.com/RazeenLI/FADTI

Runze Li, Hanchen Wang, Wenjie Zhang +4

University of New South Wales, Australia · University of Technology Sydney, Australia · The Chinese University of Hong Kong, Shenzhen, China

Frequency-Domain Time Series ModelingTime Series ImputationIncomplete Data ImputationDiffusion Models
AskPDF
Aug 3, 2026

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

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.

Mingyang Wang, Rongwen Li, Xiao Wang +1

College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan, China

Time Series ImputationLearning with Missing Data
AskPDF