Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2212.10306 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912443231371264 |
|---|---|
| author | Cheng, Yunyao Guo, Chenjuan Chen, Kaixuan Zhao, Kai Yang, Bin Xie, Jiandong Jensen, Christian S. Huang, Feiteng Zheng, Kai |
| author_facet | Cheng, Yunyao Guo, Chenjuan Chen, Kaixuan Zhao, Kai Yang, Bin Xie, Jiandong Jensen, Christian S. Huang, Feiteng Zheng, Kai |
| contents | Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in fields like physics and biology poses significant challenges. Existing models struggle to capture long-term dependencies and to model diverse meta-knowledge explicitly in few-shot scenarios. To address these issues, we propose MetaGP, a meta-learning-based Gaussian process latent variable model that uses a Gaussian process kernel function to capture long-term dependencies and to maintain strong correlations in time series. We also introduce Kernel Association Search (KAS) as a novel meta-learning component to explicitly model meta-knowledge, thereby enhancing both interpretability and prediction accuracy. We study MetaGP on simulated and real-world few-shot datasets, showing that it is capable of state-of-the-art prediction accuracy. We also find that MetaGP can capture long-term dependencies and can model meta-knowledge, thereby providing valuable insights into complex time series patterns. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_10306 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting Cheng, Yunyao Guo, Chenjuan Chen, Kaixuan Zhao, Kai Yang, Bin Xie, Jiandong Jensen, Christian S. Huang, Feiteng Zheng, Kai Machine Learning Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in fields like physics and biology poses significant challenges. Existing models struggle to capture long-term dependencies and to model diverse meta-knowledge explicitly in few-shot scenarios. To address these issues, we propose MetaGP, a meta-learning-based Gaussian process latent variable model that uses a Gaussian process kernel function to capture long-term dependencies and to maintain strong correlations in time series. We also introduce Kernel Association Search (KAS) as a novel meta-learning component to explicitly model meta-knowledge, thereby enhancing both interpretability and prediction accuracy. We study MetaGP on simulated and real-world few-shot datasets, showing that it is capable of state-of-the-art prediction accuracy. We also find that MetaGP can capture long-term dependencies and can model meta-knowledge, thereby providing valuable insights into complex time series patterns. |
| title | Gaussian Process Latent Variable Modeling for Few-shot Time Series Forecasting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2212.10306 |