AI Paper Atlas

Research map / Time series / Long-term forecasting

Pay Attention to Evolution: Time Series Forecasting With Deep Graph-Evolution Learning

Gabriel Spadon, Shenda Hong, Bruno Brandoli Machado, Stan Matwin, Jose Fernando Rodrigues Junior, Jimeng Sun

TPAMI 2021 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 78 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 GSE layers (full ReGENN vs best no-GSE ablation) (ablation)ReGENN · SARS-CoV-2MAE, RMSE, MSLE: 20.81% MAE, 19.77% RMSE, 35.72% MSLEImproved
add GSE layers over best no-GSE ablation (ablation)ReGENN · Brazilian WeatherMAE, RMSE: 8.42% on the MAE and 2.16% on the RMSEImproved
add GSE layers over bidirectional LSTM decoder (ablation)ReGENN · PhysioNet 2012MAE, RMSE: 1.05% on the MAE and 0.98% on the RMSEImproved
add Autoregression component (ablation)ReGENN · SARS-CoV-2MAE: 8208.53 -> 165.41Improved
add Autoregression component (ablation)ReGENN · Brazilian WeatherMAE: 2.00 -> 1.92Improved
add Autoregression component (ablation)ReGENN · PhysioNet 2012RMSE: 49.72 -> 47.31Improved
add variable-axis decoder (ablation)ReGENN · SARS-CoV-2MSLE: 0.15 -> 0.05Improved
add variable-axis decoder (ablation)ReGENN · Brazilian WeatherMSLE: 0.27 -> 0.28No clear effect
add variable-axis decoder (ablation)ReGENN · PhysioNet 2012MAE: 18.23 -> 18.22No clear effect
combine network with Autoregression instead of Autoregression only (ablation)ReGENN · SARS-CoV-2MAE: 11529.79 -> 165.41Improved
use ReGENN instead of ensemble baselines (second-best Exponential Smoothing)ReGENN · SARS-CoV-2 (120 days)MAE, RMSE, MSLE: 75.21% on the MAE, 64.87% on the RMSE, and 79.61% on the MSLEImproved
use ReGENN instead of Elman RNNReGENN · Brazilian WeatherMAE, RMSE, MSLE: 11.95% on the MAE, 11.96% on the RMSE, and 25.84% on the MSLEImproved

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