AI Paper Atlas

Research map / Time series / Long-term forecasting

Learning Latent Seasonal-Trend Representations for Time Series Forecasting

Zhiyuan Wang, Xovee Xu, Weifeng Zhang, Goce Trajcevski, Ting Zhong, Fan Zhou

NeurIPS 2022 · Time series › Long-term forecasting · approach: Graph-based multivariate forecasting · 5 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 seasonal component (ablation)LaST · Synthetic, horizon 24MSE: 0.179 -> 0.129Improved
add trend component (ablation)LaST · Synthetic, horizon 24MSE: 2.870 -> 0.129Improved
add trend component (ablation)LaST · ETTh1 multivariate, horizon 24MSE: 0.631 -> 0.324Improved
add seasonal component (ablation)LaST · ETTh1 multivariate, averageMSE: 0.631 -> 0.533Improved
add autocorrelation and CORT coefficients in reconstruction loss (ablation)LaST · ETTh1 multivariate, horizon 24MSE: 0.334 -> 0.324Improved
add MI lower bound regularization (ablation)LaST · ETTh1 multivariate, horizon 24MSE: 0.339 -> 0.324Improved
add MI upper bound regularization (ablation)LaST · ETTh1 multivariate, horizon 24MSE: 0.332 -> 0.324Improved
use proposed unbiased MI lower bound instead of MINE (ablation)LaST · ETTh1 multivariate, horizon 24MSE: 0.332 -> 0.324Improved
use proposed lower bound instead of MINE on ETTh1 horizon 720 (ablation)LaST · ETTh1 multivariate, horizon 720MSE: 0.780 -> 0.740Improved
MINE vs no MI lower bound (w/o lower) on ETTh1 horizon 720 (ablation)LaST · ETTh1 multivariate, horizon 720MSE: 0.766 -> 0.780Hurt
longer input length (96 to 672) for LaST at output 672LaST · ETTm1 multivariateMSE: 0.532 -> 0.463Improved
longer input length (201 to 672) for LaST at output 48LaST · ETTm1 multivariateMSE: 0.280 -> 0.279No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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