AI Paper Atlas

Research map / Time series / Foundation models for time series

CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting

Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

ICLR 2022 · Time series › Foundation models for time series · approach: Time series representation learning · 87 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
learn disentangled trend and seasonal representations with contrastive lossesCoST · Multivariate forecasting, averageMSE: 0.750 -> 0.590Improved
add seasonal representations to the trend-only model (ablation)CoST · ETT datasets, multivariateMSE: 0.789 -> 0.781Improved
add the mixture of autoregressive experts (ablation)CoST trend branch · ETT datasets, multivariateMSE: 0.882 -> 0.789Improved
add the learnable Fourier layer (ablation)CoST seasonal branch · ETT datasets, multivariateMSE: 0.895 -> 0.862Improved
add frequency-domain contrastive loss (ablation)CoST seasonal branch · ETT datasets, multivariateMSE: 0.905 -> 0.862Improved
train the architecture end-to-end with supervised forecasting loss instead of the representation-learning pipeline (ablation)CoST · ETT datasets, multivariateMSE: 0.781 -> 1.376Hurt
add contrastive loss to end-to-end supervised forecasting training (ablation)CoST · ETT datasets, multivariateMSE: 1.376 -> 1.477Hurt
replace the TCN backbone with LSTM (ablation)CoST · ETT datasets, multivariateMSE: 0.781 -> 0.928Hurt
replace the TCN backbone with Transformer (ablation)CoST · ETT datasets, multivariateMSE: 0.781 -> 0.863Hurt
replace ridge regression with linear regression (ablation)CoST · ETT datasets, multivariateMSE: 0.781 -> 1.472Hurt
replace ridge regression with kernel ridge regression (ablation)CoST · ETT datasets, multivariateMSE: 0.781 -> 0.868Hurt
vary the seasonal-loss weight alpha (ablation)CoST · ETT datasets, univariate and multivariateMSE: Multivariate: 0.810 to 0.780; Univariate: 0.120 to 0.102Mixed

Later papers that compared with this method

7 later accepted papers report CoST as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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