Automated Contrastive Learning Strategy Search for Time Series
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917812884209664 |
|---|---|
| author | Jing, Baoyu Wang, Yansen Sui, Guoxin Hong, Jing He, Jingrui Yang, Yuqing Li, Dongsheng Ren, Kan |
| author_facet | Jing, Baoyu Wang, Yansen Sui, Guoxin Hong, Jing He, Jingrui Yang, Yuqing Li, Dongsheng Ren, Kan |
| contents | In recent years, Contrastive Learning (CL) has become a predominant representation learning paradigm for time series. Most existing methods manually build specific CL Strategies (CLS) by human heuristics for certain datasets and tasks. However, manually developing CLS usually requires excessive prior knowledge about the data, and massive experiments to determine the detailed CL configurations. In this paper, we present an Automated Machine Learning (AutoML) practice at Microsoft, which automatically learns CLS for time series datasets and tasks, namely Automated Contrastive Learning (AutoCL). We first construct a principled search space of size over $3\times10^{12}$, covering data augmentation, embedding transformation, contrastive pair construction, and contrastive losses. Further, we introduce an efficient reinforcement learning algorithm, which optimizes CLS from the performance on the validation tasks, to obtain effective CLS within the space. Experimental results on various real-world datasets demonstrate that AutoCL could automatically find the suitable CLS for the given dataset and task. From the candidate CLS found by AutoCL on several public datasets/tasks, we compose a transferable Generally Good Strategy (GGS), which has a strong performance for other datasets. We also provide empirical analysis as a guide for the future design of CLS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_12641 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automated Contrastive Learning Strategy Search for Time Series Jing, Baoyu Wang, Yansen Sui, Guoxin Hong, Jing He, Jingrui Yang, Yuqing Li, Dongsheng Ren, Kan Machine Learning In recent years, Contrastive Learning (CL) has become a predominant representation learning paradigm for time series. Most existing methods manually build specific CL Strategies (CLS) by human heuristics for certain datasets and tasks. However, manually developing CLS usually requires excessive prior knowledge about the data, and massive experiments to determine the detailed CL configurations. In this paper, we present an Automated Machine Learning (AutoML) practice at Microsoft, which automatically learns CLS for time series datasets and tasks, namely Automated Contrastive Learning (AutoCL). We first construct a principled search space of size over $3\times10^{12}$, covering data augmentation, embedding transformation, contrastive pair construction, and contrastive losses. Further, we introduce an efficient reinforcement learning algorithm, which optimizes CLS from the performance on the validation tasks, to obtain effective CLS within the space. Experimental results on various real-world datasets demonstrate that AutoCL could automatically find the suitable CLS for the given dataset and task. From the candidate CLS found by AutoCL on several public datasets/tasks, we compose a transferable Generally Good Strategy (GGS), which has a strong performance for other datasets. We also provide empirical analysis as a guide for the future design of CLS. |
| title | Automated Contrastive Learning Strategy Search for Time Series |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.12641 |