Label-efficient Time Series Representation Learning: A Review
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914884000677888 |
|---|---|
| author | Eldele, Emadeldeen Ragab, Mohamed Chen, Zhenghua Wu, Min Kwoh, Chee-Keong Li, Xiaoli |
| author_facet | Eldele, Emadeldeen Ragab, Mohamed Chen, Zhenghua Wu, Min Kwoh, Chee-Keong Li, Xiaoli |
| contents | Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time series data, various strategies, e.g., transfer learning, self-supervised learning, and semi-supervised learning, have been developed. In this survey, we introduce a novel taxonomy for the first time, categorizing existing approaches as in-domain or cross-domain, based on their reliance on external data sources or not. Furthermore, we present a review of the recent advances in each strategy, conclude the limitations of current methodologies, and suggest future research directions that promise further improvements in the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_06433 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Label-efficient Time Series Representation Learning: A Review Eldele, Emadeldeen Ragab, Mohamed Chen, Zhenghua Wu, Min Kwoh, Chee-Keong Li, Xiaoli Machine Learning Label-efficient time series representation learning, which aims to learn effective representations with limited labeled data, is crucial for deploying deep learning models in real-world applications. To address the scarcity of labeled time series data, various strategies, e.g., transfer learning, self-supervised learning, and semi-supervised learning, have been developed. In this survey, we introduce a novel taxonomy for the first time, categorizing existing approaches as in-domain or cross-domain, based on their reliance on external data sources or not. Furthermore, we present a review of the recent advances in each strategy, conclude the limitations of current methodologies, and suggest future research directions that promise further improvements in the field. |
| title | Label-efficient Time Series Representation Learning: A Review |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2302.06433 |