AI Paper Atlas

Research map / Time series / Long-term forecasting

RI-Loss: A Learnable Residual-Informed Loss for Time Series Forecasting

Jieting Wang, Xiaolei Shang, Feijiang Li, Furong Peng

AAAI 2026 · Time series › Long-term forecasting · approach: Attention for time series 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
train with RI-Loss instead of MSEInformer · ETTh2 (H=96)MSE: 3.340 -> 2.299Improved
train with RI-Loss instead of MSEDLinear · ETTh2 (H=720)MSE: 0.696 -> 0.582Improved
train with RI-Loss instead of MSEDLinear · Exchange (H=336)MSE: 0.345 -> 0.265Improved
train with RI-Loss instead of MSEDLinear · ILI (H=60)MSE: 2.410 -> 1.970Improved
train with RI-Loss instead of MSEInformer · Exchange (H=720)MSE: 2.206 -> 2.574Hurt
train with RI-Loss instead of MSEInformer · Electricity (H=720)MSE: 0.341 -> 0.367Hurt
use HSIC dependence term instead of Pearson correlation (ablation)DLinear · ETTh2 (H=96)MSE: 0.305 -> 0.279Improved
use HSIC dependence term instead of Pearson correlation (ablation)Informer · ETTh2 (H=96)MSE: 2.569 -> 2.299Improved
use HSIC dependence term instead of Pearson correlation (ablation)DLinear · ETTh2 (H=720)MSE: 0.714 -> 0.582Improved
use RI-Loss instead of MAE loss (ablation)DLinear · ETTh2 (H=720)MSE: 0.590 -> 0.582Improved
use RI-Loss instead of MAE loss (ablation)Informer · ETTh2 (H=720)MSE: 3.083 -> 3.094Hurt
train with RI-Loss under input noise (SNR -3dB)DLinear · ETTh2 H=720 noise -3dBMSE: 0.693 -> 0.579Improved

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