Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version)
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917184904626176 |
|---|---|
| author | Liu, Yuansan Wijewickrema, Sudanthi Li, Ang Bester, Christofer O'Leary, Stephen Bailey, James |
| author_facet | Liu, Yuansan Wijewickrema, Sudanthi Li, Ang Bester, Christofer O'Leary, Stephen Bailey, James |
| contents | Generating time series data is a promising approach to address data deficiency problems. However, it is also challenging due to the complex temporal properties of time series data, including local correlations as well as global dependencies. Most existing generative models have failed to effectively learn both the local and global properties of time series data. To address this open problem, we propose a novel time series generative model named 'Time-Transformer AAE', which consists of an adversarial autoencoder (AAE) and a newly designed architecture named 'Time-Transformer' within the decoder. The Time-Transformer first simultaneously learns local and global features in a layer-wise parallel design, combining the abilities of Temporal Convolutional Networks and Transformer in extracting local features and global dependencies respectively. Second, a bidirectional cross attention is proposed to provide complementary guidance across the two branches and achieve proper fusion between local and global features. Experimental results demonstrate that our model can outperform existing state-of-the-art models in 5 out of 6 datasets, specifically on those with data containing both global and local properties. Furthermore, we highlight our model's advantage on handling this kind of data via an artificial dataset. Finally, we show our model's ability to address a real-world problem: data augmentation to support learning with small datasets and imbalanced datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_11714 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version) Liu, Yuansan Wijewickrema, Sudanthi Li, Ang Bester, Christofer O'Leary, Stephen Bailey, James Machine Learning Artificial Intelligence Generating time series data is a promising approach to address data deficiency problems. However, it is also challenging due to the complex temporal properties of time series data, including local correlations as well as global dependencies. Most existing generative models have failed to effectively learn both the local and global properties of time series data. To address this open problem, we propose a novel time series generative model named 'Time-Transformer AAE', which consists of an adversarial autoencoder (AAE) and a newly designed architecture named 'Time-Transformer' within the decoder. The Time-Transformer first simultaneously learns local and global features in a layer-wise parallel design, combining the abilities of Temporal Convolutional Networks and Transformer in extracting local features and global dependencies respectively. Second, a bidirectional cross attention is proposed to provide complementary guidance across the two branches and achieve proper fusion between local and global features. Experimental results demonstrate that our model can outperform existing state-of-the-art models in 5 out of 6 datasets, specifically on those with data containing both global and local properties. Furthermore, we highlight our model's advantage on handling this kind of data via an artificial dataset. Finally, we show our model's ability to address a real-world problem: data augmentation to support learning with small datasets and imbalanced datasets. |
| title | Time-Transformer: Integrating Local and Global Features for Better Time Series Generation (Extended Version) |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2312.11714 |