Soft Contrastive Learning for Time Series

Understand

Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way.

• However, contrasting similar time series instances or values from adjacent timestamps within a time series leads to ignore their inherent correlations, which results in deteriorating the quality of learned representations.
• To address this issue, we propose SoftCLT, a simple yet effective soft contrastive learning strategy for time series.
• This is achieved by introducing instance-wise and temporal contrastive loss with soft assignments ranging from zero to one.