AI Paper Atlas

Research map / Time series / Foundation models for time series

ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning

Caiyi Yang, Chenglin Li, Hao Zhang, Weijia Lu, ZHIFEI YANG, Wenrui Dai, xiaodong Zhang, Xiaofeng Ma, Can Zhang, Junni Zou, Hongkai Xiong

ICML 2026 · Time series › Foundation models for time series · approach: Time series representation learning

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
use prototype-guided semantic augmentation instead of AutoTCL's augmentationProSAR · Univariate forecasting avgMSE: 0.161 -> 0.151Improved
use prototype-guided semantic augmentation instead of AutoTCL's augmentationProSAR · Multivariate forecasting avgMSE: 0.571 -> 0.561Improved
add DTW-based semantic segmentation (ablation)ProSAR · Univariate forecastingMSE: 0.172 -> 0.151Improved
add frequency (STFT) alignment (ablation)ProSAR · Univariate forecastingMSE: 0.178 -> 0.151Improved
add dynamic clustering of prototypes (ablation)ProSAR · Univariate forecastingMSE: 0.175 -> 0.151Improved
add decoder feedback (ablation)ProSAR · Univariate forecastingMSE: 0.164 -> 0.151Improved
add dual prototypes for input-space grounding (ablation)ProSAR · Univariate forecastingMSE: 0.158 -> 0.151Improved
apply ProSAR instead of FreRA in data-scarce transferProSAR · SHAR transfer, 3 source domainsaccuracy: 0.525 -> 0.553Improved
apply ProSAR instead of FreRA with 19 source domainsProSAR · SHAR transfer, 19 sources, target 5accuracy: 0.698 -> 0.695No clear effect
apply ProSAR instead of FreRA with 1% labelsProSAR · Semi-supervised 1% labels avgaccuracy: 0.836 -> 0.853Improved
add DTW prototype alignment to trainingProSAR · training costtraining time: 2.5% increase in total training timeNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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