AI Paper Atlas

Research map / Time series / Long-term forecasting

Towards Better Forecasting by Fusing Near and Distant Future Visions

Jiezhu Cheng, Kaizhu Huang, Zibin Zheng

AAAI 2020 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 60 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
Fuse near- and distant-future task representations with MLCNN instead of LSTNetMultivariate forecasting · TrafficRMSE: 4.09%, 5.04%, 4.64%Improved
Fuse near- and distant-future task representations with MLCNN instead of LSTNetMultivariate forecasting · TrafficMAE: 5.17%, 8.13%, 7.32%Improved
Use MLCNN rather than AECRNNMultivariate forecasting · Traffic, Energy, NASDAQRMSE and MAEImproved
Remove different abstraction levels between task construals (ablation)MLCNN · Three forecasting datasetsRMSE and MAEHurt
Remove the shared fusion LSTM (ablation)MLCNN · Three forecasting datasetsRMSE and MAEHurt
Remove the main-task decoder LSTM (ablation)MLCNN · Three forecasting datasetsRMSE and MAEHurt
Add the autoregressive component (ablation)MLCNN · Most datasetsRMSE and MAEImproved
Remove the autoregressive component (ablation)LSTNet · Three forecasting datasetsRMSE and MAEHurt

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