Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916624862281728 |
|---|---|
| author | Wang, Wenxuan Wu, Kai Li, Yujian Betterest Wang, Dan Zhang, Xiaoyu Liu, Jing |
| author_facet | Wang, Wenxuan Wu, Kai Li, Yujian Betterest Wang, Dan Zhang, Xiaoyu Liu, Jing |
| contents | Foundation models for time series analysis (TSA) have attracted significant attention. However, challenges such as data scarcity and data imbalance continue to hinder their development. To address this, we consider modeling complex systems through symbolic expressions that serve as semantic descriptors of time series. Building on this concept, we introduce a series-symbol (S2) dual-modulity data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic representations. Leveraging the S2 dataset, we develop SymTime, a pre-trained foundation model for TSA. SymTime demonstrates competitive performance across five major TSA tasks when fine-tuned with downstream task, rivaling foundation models pre-trained on real-world datasets. This approach underscores the potential of dual-modality data generation and pretraining mechanisms in overcoming data scarcity and enhancing task performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15466 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation Wang, Wenxuan Wu, Kai Li, Yujian Betterest Wang, Dan Zhang, Xiaoyu Liu, Jing Machine Learning Artificial Intelligence Foundation models for time series analysis (TSA) have attracted significant attention. However, challenges such as data scarcity and data imbalance continue to hinder their development. To address this, we consider modeling complex systems through symbolic expressions that serve as semantic descriptors of time series. Building on this concept, we introduce a series-symbol (S2) dual-modulity data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic representations. Leveraging the S2 dataset, we develop SymTime, a pre-trained foundation model for TSA. SymTime demonstrates competitive performance across five major TSA tasks when fine-tuned with downstream task, rivaling foundation models pre-trained on real-world datasets. This approach underscores the potential of dual-modality data generation and pretraining mechanisms in overcoming data scarcity and enhancing task performance. |
| title | Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.15466 |