2026
ProSAR: Prototype-Guided Semantic Augmentation and Refinement for Time Series Contrastive Learning
ICML 2026poster
Contrastive learning has advanced the representation learning across domains, yet its success relies on data augmentations that preserve semantic contents while providing the view diversities. Multivariate time series, however, are inherently noisy, non-stationary, and lack such intuitive semantic c…