Automated Contrastive Learning Strategy Search for Time Series

arXiv:2403.12641v1 Announce Type: new
Abstract: In recent years, Contrastive Learning (CL) has become a predominant representation learning paradigm for time series. Most existing methods in the literature focus on manually building specific Contrastive Learning Strategies (CLS) by human heuristics for certain datasets and tasks. However, manually developing CLS usually require excessive prior knowledge about the datasets and tasks, e.g., professional cognition of the medical time series in healthcare, as well as huge human labor and massive experiments to determine the …

abstract arxiv automated become building cs.lg datasets focus heuristics however human literature paradigm prior representation representation learning search series strategies strategy tasks time series type