AI Paper Atlas

Research map / Time series / Long-term forecasting

Correlation Recurrent Units: A Novel Neural Architecture for Improving the Predictive Performance of Time-Series Data

Sunghyun Sim, Dohee Kim, Hyerim Bae

TPAMI 2023 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 26 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 the STL cell inside the recurrent cellRNN · UTD1 US GDP, 1-stepRMSE: 120.707 -> 110.712Improved
add the STL cell inside the cell instead of STL decomposition across separate networksRNN · UTD1 US GDP, 1-stepRMSE: 112.889 -> 110.712Improved
apply network-level STL decomposition with separate RNNsRNN · UTD1 US GDP, 1-stepRMSE: 120.707 -> 112.889Improved
add autocorrelation and correlation gates to the STL cell (ablation)RNN-STLC · UTD1 US GDP, 1-stepRMSE: 110.712 -> 104.766Improved
add autocorrelation and correlation gates to the STL cell (ablation)RNN-STLC · MTD3 world stock indices, 1-stepRMSE: 107.55 -> 95.17Improved
add autocorrelation and correlation gates to the STL cell (ablation)RNN-STLC · MTD1 big-tech stocks, 1-stepRMSE: 21.28 -> 20.15Improved
use STL cell instead of STL decompositionLSTM-STLD · MTD3 world stock indices, 1-stepRMSE: 184.89 -> 115.91Improved
replace DSANet with CRUDSANet · MTD1 big-tech stocks, 1-stepRMSE: 28.32 -> 20.15Improved
replace DSANet with CRUDSANet · MTD2 Baltic dry indices, 6-stepRMSE: 184.18 -> 167.26Improved
replace DSANet with CRUDSANet · MTD3 world stock indices, 12-stepRMSE: 432.70 -> 499.03Hurt
replace DSANet with CRUDSANet · MTD1 big-tech stocks, 12-stepRMSE: 95.27 -> 96.49Hurt
replace LSTNet-A with CRULSTNet-A · MTD2 Baltic dry indices, 12-stepRMSE: 285.21 -> 270.16Improved

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