Time-Transformer: Integrating Local and Global Features for Better Time Series Generation
CoRR(2023)
摘要
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.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要