Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects

arXiv:2306.10125v3 Announce Type: replace
Abstract: Self-supervised learning (SSL) has recently achieved impressive performance on various time series tasks. The most prominent advantage of SSL is that it reduces the dependence on labeled data. Based on the pre-training and fine-tuning strategy, even a small amount of labeled data can achieve high performance. Compared with many published self-supervised surveys on computer vision and natural language processing, a comprehensive survey for time series SSL is still missing. To fill this gap, we review …

abstract analysis arxiv cs.ai cs.lg data eess.sp fine-tuning performance pre-training progress prospects self-supervised learning series small ssl stat.ap strategy supervised learning tasks taxonomy time series training type