AI Paper Atlas

Research map / Time series / Long-term forecasting

DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting

Siru Zhong, Yiqiu Liu, Zhiqing Cui, Zezhi Shao, Fei Wang, Qingsong Wen, Yuxuan Liang

ICML 2026 · Time series › Long-term forecasting · approach: Attention for time series 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 DropoutTS to InformerInformer · Synth-12MSE avg improvement: 46.0% avg MSE reductionImproved
add DropoutTS to PatchTST, iTransformer, TimeMixerstrong backbones · Synth-12MSE: 0.7% to 2.8%Improved
add DropoutTS to PatchTST on ETTm2PatchTST · ETTm2MSE: 0.280 -> 0.280 (0.0%)No clear effect
remove global linear detrending (ablation)DropoutTS · Synth-12MSE: 1.076 -> 1.642 without (41.7% worse than baseline)Improved
add SFM anchor to threshold (ablation)DropoutTS · Synth-12MSE: 1.520 -> 1.076Improved
add log-scale spectral normalization (ablation)DropoutTS · Synth-12MSE: 1.308 -> 1.076Improved
use robust OLS detrend instead of simple detrend (ablation)DropoutTS · Synth-12MSE: 1.574 -> 1.076Improved
initial sensitivity gamma 1.0 vs 5.0 vs 10.0 (ablation)DropoutTS · Synth-12MSEMixed
add DropoutTS to PatchTST in few-shot ILI (10% data)PatchTST · ILI few-shotMAE: 1.333 -> 1.295Improved
add DropoutTS to PatchTST at 50% ILI dataPatchTST · ILI few-shot (50% data)MSE: 3.143 -> 3.169Hurt
add DropoutTS to PatchTST for zero-shot transferPatchTST · ETT cross-dataset transferMAE: 0.402 -> 0.395 avgImproved
hard low-pass denoising of input instead of DropoutTS (ablation)PatchTST/TimeMixer · ILIMAE: PatchTST 1.110 -> 1.162Hurt

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