AI Paper Atlas

Research map / Time series / Long-term forecasting

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

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

ICLR 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add cross-variable attention instead of pointwise convolution (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.037 -> 0.033Improved
add cross-variable modeling at all (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.051 -> 0.033Improved
use one-to-one channel-head binding instead of 32 channels per head (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.037 -> 0.033Improved
use one-to-one binding instead of 16 channels per head (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.038 -> 0.033Improved
use one-to-one binding instead of 8 channels per head (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.035 -> 0.033Improved
add explicit mask channel to the input embedding (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.034 -> 0.033Improved
use PixelShuffle instead of linear upsampling (ablation)T1 · ETT/Weather/Electricity avgMSE: 0.034 -> 0.033Improved
use T1 instead of PatchTST at 70% missingT1 · Point missing ratio 0.7MSE: 0.092 -> 0.049Improved
use T1 under block missingT1 · Block missingMSE: 0.050 -> 0.026Improved
use T1 on naturally missing dataT1 · PhysioNet2012 and AQI36MSE: 0.097 -> 0.075 (PhysioNet); 0.262 -> 0.226 (AQI36)Improved
use T1 on Weather with MAET1 · Weather (point missing)MSE: MAE 0.045 vs 0.042 (BRITS)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy