AI Paper Atlas

Research map / Time series / Long-term forecasting

Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting

Boyuan Li, Zhen Liu, Yicheng Luo, Qianli Ma

ICLR 2026 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 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 ReIMTS recursive multi-scale wrapper to GraFITiGraFITi · MIMIC-IVMSE x10^-1: 2.39 -> 1.79Improved
add ReIMTS to GraFITiGraFITi · MIMIC-IIIMSE x10^-1: 4.08 -> 4.07No clear effect
add ReIMTS to PrimeNetPrimeNet · Human ActivityMSE x10^-1: 26.84 -> 0.82Improved
add ReIMTS to six IMTS backbonessix IMTS backbones · five IMTS datasetsMSE: average 27.1% error reductionImproved
add ReIMTS to GRU-DGRU-D · PhysioNet'12MSE x10^-1: 3.25 -> 3.25No clear effect
split subsamples by time period instead of observation count (ablation)ReIMTS (GraFITi) · MIMIC-IVMSE x10^-1: 2.36 -> 1.79Improved
add recursive splitting into subsamples (vs original sample only) (ablation)ReIMTS (GraFITi) · MIMIC-IIIMSE x10^-1: 4.99 -> 4.07Improved
use irregularity-aware fusion instead of simple addition (ablation)ReIMTS (GraFITi) · USHCNMSE x10^-1: 1.89 -> 1.66Improved
use irregularity-aware fusion instead of simple addition (ablation)ReIMTS (GraFITi) · PhysioNet'12MSE x10^-1: 2.79 -> 2.83Hurt
add fusion of global and local representations (vs none) (ablation)ReIMTS (GraFITi) · MIMIC-IIIMSE x10^-1: 4.77 -> 4.07Improved
increase scale levels from 2 to 3 (ablation)ReIMTS (GraFITi) · Human ActivityMSE x10^-1: 0.42 -> 0.71Hurt
increase scale levels from 2 to 3 (ablation)ReIMTS (GraFITi) · MIMIC-IIIMSE x10^-1: 4.09 -> 4.07No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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