AI Paper Atlas

Research map / Time series / Foundation models for time series

Beyond Observations: Reconstruction Error-Guided Irregularly Sampled Time Series Representation Learning

Jiexi Liu, Meng Cao, Songcan Chen

AAAI 2026 · Time series › Foundation models for time series · approach: Time series representation learning · 1 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 pseudo-observations from reconstruction-error mixup (ablation)iTimER pretraining · PhysioNet interpolationMSE x1e-3: 5.03 -> 2.86Improved
add pseudo-observations (ablation)iTimER pretraining · PhysioNet forecastingMSE x1e-3: 6.10 -> 3.64Improved
add pseudo-observations (ablation)iTimER pretraining · P12AUROC: 84.6 -> 85.7Improved
use mixup of error with last observation instead of random or constant values (ablation)iTimER · PhysioNet interpolationMSE x1e-3: 4.01 / 3.89 -> 2.86Improved
anchor error samples to an observed value instead of error only (ablation)iTimER · PhysioNet interpolationMSE x1e-3: 3.08 -> 2.86Improved
add Wasserstein loss (ablation)iTimER · PhysioNet interpolationMSE x1e-3: 3.17 -> 2.86Improved
add contrastive loss (ablation)iTimER · PhysioNet interpolationMSE x1e-3: 3.02 -> 2.86Improved
use moving average anchor instead of last observation (ablation)iTimER · PhysioNet interpolationMSE x1e-3: 2.86 -> 2.83No clear effect
use iTimER instead of ViTST/Warpformerclassification · P19AUROC: AUROC 87.1 vs ViTST 89.2Hurt
use iTimER instead of ISTS-PLMforecasting · Human ActivityMSE x1e-3: 2.75 vs 2.58Hurt
use iTimER instead of ISTS-PLMinterpolation · MIMICMSE x1e-2: 1.47 -> 0.13Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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