Simple Contrastive Representation Learning for Time Series Forecasting
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916477222780928 |
|---|---|
| author | Zheng, Xiaochen Chen, Xingyu Schürch, Manuel Mollaysa, Amina Allam, Ahmed Krauthammer, Michael |
| author_facet | Zheng, Xiaochen Chen, Xingyu Schürch, Manuel Mollaysa, Amina Allam, Ahmed Krauthammer, Michael |
| contents | Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification. However, these methods are less effective for time series forecasting, as optimization of instance discrimination is not directly applicable to predicting the future state from the historical context. To address these limitations, we propose SimTS, a simple representation learning approach for improving time series forecasting by learning to predict the future from the past in the latent space. SimTS exclusively uses positive pairs and does not depend on negative pairs or specific characteristics of a given time series. In addition, we show the shortcomings of the current contrastive learning framework used for time series forecasting through a detailed ablation study. Overall, our work suggests that SimTS is a promising alternative to other contrastive learning approaches for time series forecasting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_18205 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Simple Contrastive Representation Learning for Time Series Forecasting Zheng, Xiaochen Chen, Xingyu Schürch, Manuel Mollaysa, Amina Allam, Ahmed Krauthammer, Michael Machine Learning Contrastive learning methods have shown an impressive ability to learn meaningful representations for image or time series classification. However, these methods are less effective for time series forecasting, as optimization of instance discrimination is not directly applicable to predicting the future state from the historical context. To address these limitations, we propose SimTS, a simple representation learning approach for improving time series forecasting by learning to predict the future from the past in the latent space. SimTS exclusively uses positive pairs and does not depend on negative pairs or specific characteristics of a given time series. In addition, we show the shortcomings of the current contrastive learning framework used for time series forecasting through a detailed ablation study. Overall, our work suggests that SimTS is a promising alternative to other contrastive learning approaches for time series forecasting. |
| title | Simple Contrastive Representation Learning for Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2303.18205 |