AI Paper Atlas

Research map / Time series / Long-term forecasting

IdealTSF: Can Non-Ideal Data Contribute to Enhancing the Performance of Time Series Forecasting Models?

Hua Wang, Jinghao Lu, Fan Zhang

AAAI 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 negative sample pre-training (ablation)IdealTSF · ETTh2MSE: 0.420 -> 0.338Improved
add negative sample pre-training (ablation)IdealTSF · ETTm1MSE: 0.465 -> 0.409Improved
add negative sample pre-training (ablation)IdealTSF · ETTm2MSE: 0.301 -> 0.247Improved
add negative sample pre-training (ablation)IdealTSF · ETTh1MSE: 0.436 -> 0.402Improved
add positive sample generation (ablation)IdealTSF · ETTh2MSE: 0.347 -> 0.338Improved
add positive sample generation (ablation)IdealTSF · ETTm1MSE: 0.417 -> 0.409Improved
add EcoSystem Optimizer (ECOS) (ablation)IdealTSF · ETTh2MSE: 0.388 -> 0.338Improved
add EcoSystem Optimizer (ECOS) (ablation)IdealTSF · ETTm2MSE: 0.270 -> 0.247Improved
add ECOS on top of negative-sample-free model (ablation)IdealTSF · ETTm1MSE: 0.468 -> 0.436Improved
use IdealTSF instead of Twinformer / TimeMixer++IdealTSF · PEMS07 and ETTm1MSE: PEMS07 0.118 vs Twinformer 0.094; ETTm1 0.409 vs TimeMixer++ 0.369Hurt
add ECOS optimizer to Adam or SGD (ablation)CIFAR-10 classifier · CIFAR-10accuracy (%): 80 -> 90 (Adam); 80 -> nearly 90 (SGD)Improved
use ECOS instead of SGD/RMSprop under PGD attack (ablation)IdealTSF · adversarial robustness (FGSM/PGD)test accuracy (%)Improved

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