AI Paper Atlas

Research map / Time series / Long-term forecasting

Efficiently Enhancing Long-term Series Forecasting via Adaptive Lookback with Wavelets

Suxin Tong, Jingling Yuan

AAAI 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 2 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 ALW plug-in (L=512 to H=256) to backbonesTQNet, CycleNet, iTransformer, DLinear · 8 datasets (ETT, Weather, Exchange, ECL, Traffic)MSE: average MSE reduction 3.2%Improved
add ALW to DLinearDLinear · 8 datasetsMSE: 5.1% average reductionImproved
add ALW to DLinearDLinear · ETTh2 (F=720)MSE: 0.605 -> 0.426Improved
add ALW to ECL/Exchange backbonesCycleNet · ECL (F=96)MSE: 0.126 -> 0.126No clear effect
add Multi-scale Decomposition Module (ablation)CycleNet+ALW · WeatherMSE: 0.240 -> 0.220Improved
add Adaptive Lookback Window Learning Module (ablation)CycleNet+ALW · ETTh1MSE: 0.419 -> 0.412Improved
add Weighted Reconstruction Module (ablation)CycleNet+ALW · ETTh1MSE: 0.448 -> 0.412Improved
add positional encoding in reconstruction (ablation)CycleNet+ALW · ETTh1MSE: 0.461 -> 0.412Improved
use learnable weights instead of uniform averaging (ablation)CycleNet+ALW · ETTh1MSE: 0.472 -> 0.412Improved
use db6 wavelet and J=3 instead of other wavelets/levels (ablation)CycleNet+ALW · ETTm1MSE: 0.347 vs 0.349-0.352No clear effect
extend fixed lookback from 96 to 512 without ALW (ablation)iTransformer · ETTh1 (F=720)MSE: 0.503 -> 0.553Hurt
extend fixed lookback from 96 to 512 without ALW (ablation)CycleNet · ETTh1 (F=720)MSE: 0.520 -> 0.473Improved

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