A Survey on Time-Series Pre-Trained Models

TL;DR

This survey reviews the development, techniques, and applications of Time-Series Pre-Trained Models, highlighting their categories, transfer learning strategies, and future research directions in time-series analysis.

Contribution

It provides a comprehensive overview of TS-PTMs, including classification, experimental analysis, and insights into their advantages, limitations, and future prospects.

Findings

Transfer learning enhances time-series analysis performance.

Transformer-based models show significant promise.

Extensive experiments compare 27 methods across 434 datasets.

Abstract

Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications. Deep learning models that rely on massive labeled data have been utilized for TSM successfully. However, constructing a large-scale well-labeled dataset is difficult due to data annotation costs. Recently, pre-trained models have gradually attracted attention in the time series domain due to their remarkable performance in computer vision and natural language processing. In this survey, we provide a comprehensive review of Time-Series Pre-Trained Models (TS-PTMs), aiming to guide the understanding, applying, and studying TS-PTMs. Specifically, we first briefly introduce the typical deep learning models employed in TSM. Then, we give an overview of TS-PTMs according to the pre-training techniques. The main categories we explore include supervised, unsupervised, and self-supervised TS-PTMs. Further, extensive experiments involving 27 methods, 434 datasets, and 679 transfer learning scenarios are conducted to analyze the advantages and disadvantages of transfer learning strategies, Transformer-based models, and representative TS-PTMs. Finally, we point out some potential directions of TS-PTMs for future work.