AI Paper Atlas

Research map / Time series / Long-term forecasting

Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective

Zhiding Liu, Mingyue Cheng, Zhi Li, Zhenya Huang, Qi Liu, Yanhu Xie, Enhong Chen

NeurIPS 2023 · Time series › Long-term forecasting · approach: Attention for time series forecasting · 17 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 SAN slice-level normalizationFEDformer · Exchange avg MSEMSE: 0.474 -> 0.298 (vs RevIN)Improved
use SAN instead of RevIN/NSTFEDformer · Weather avg MSEMSE: 0.279 vs 0.268 (RevIN)Hurt
add SAN to backboneDLinear · Exchange/ILI/ETTh2 multivariateavg MSE: 7.67%, 11.13%, 21.29% MSE reductionImproved
add SAN to backboneSCINet · ETTh2 horizon 720MSE: 70.37% reductionImproved
add SAN for long input lengthsInformer · Electricity, Lin 720, Lout 720MSE: 0.9426 -> 0.2090Improved
add residual learning of mean in statistics prediction (vs removing) (ablation)SAN on Autoformer · Exchange 720MSE: 1.456 -> 0.689Improved
add residual learning of mean (ablation)SAN on Autoformer · ETTh2 720MSE: 0.889 -> 0.471Improved
add individual per-variable preference weights (ablation)SAN on Autoformer · Exchange 336MSE: 0.340 -> 0.262Improved
add individual per-variable preference weights (ablation)SAN on Autoformer · ETTh2 (96-720)MSE: 0.483 -> 0.471 at 720No clear effect
vary slicing length from 6 to 48 (ablation)SAN on SCINet · Electricity/Traffic/Weather/ETTh1/ETTh2MSE: Electricity 0.210 / 0.207 / 0.206 / 0.208No clear effect
slicing length 12 vs 24 (ablation)SAN on SCINet · ETTm1 720MSE: 0.611 (24) vs 0.450 (12)Mixed
replace joint training (Dish-TS) with SAN two-stage trainingFEDformer · Exchange avg MSEMSE: 0.704 -> 0.298Improved

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