Papers › Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate...

Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction

12 Feb 2024arXiv:2402.07570archive 2025-07-28

Cheng Feng, Long Huang, Denis Krompass

We present General Time Transformer (GTT), an encoder-only style foundation model for zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M high-quality time series samples spanning diverse domains. In our proposed framework, the task of multivariate time series forecasting is formulated as a channel-wise next curve shape prediction problem, where each time series sample is represented as a sequence of non-overlapping curve shapes with a unified numerical magnitude. GTT is trained to predict the next curve shape based on a window of past curve shapes in a channel-wise manner. Experimental results demonstrate that GTT exhibits superior zero-shot multivariate forecasting capabilities on unseen time series datasets, even surpassing state-of-the-art supervised baselines. Additionally, we investigate the impact of varying GTT model parameters and training dataset scales, observing that the scaling law also holds in the context of zero-shot multivariate time series forecasting.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large MAE 0.419 #23 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large MSE 0.424 #23 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large(Fine-tune) MAE 0.418 #32 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large(Fine-tune) MSE 0.433 #32 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Smal MAE 0.427 #46 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Smal MSE 0.459 #46 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Tiny MAE 0.436 #48 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Tiny MSE 0.466 #48 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large(100M traing samples) MAE 0.432 #49 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large(100M traing samples) MSE 0.468 #49 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large(50M traing samples) MAE 0.444 #55 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate GTT-Large(50M traing samples) MSE 0.475 #55 of 72 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections