Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification. (arXiv:2208.06616v1 [cs.LG])

Learning time-series representations when only unlabeled data or few labeled
samples are available can be a challenging task. Recently, contrastive
self-supervised learning has shown great improvement in extracting useful
representations from unlabeled data via contrasting different augmented views
of data. In this work, we propose a novel Time-Series representation learning
framework via Temporal and Contextual Contrasting (TS-TCC) that learns
representations from unlabeled data with contrastive learning. Specifically, we
propose time-series specific weak and strong augmentations and use their views
to …

arxiv classification learning lg representation representation learning semi-supervised series time