Fi$^2$VTS: Time Series Forecasting Via Capturing Intra- and Inter-Variable Variations in the Frequency Domain
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929573492424704 |
|---|---|
| author | Shen, Rujia Yang, Yang Lin, Yaoxion Liu, Liangliang Wang, Boran Guan, Yi Jiang, Jingchi |
| author_facet | Shen, Rujia Yang, Yang Lin, Yaoxion Liu, Liangliang Wang, Boran Guan, Yi Jiang, Jingchi |
| contents | Time series forecasting (TSF) plays a crucial role in various applications, including medical monitoring and crop growth. Despite the advancements in deep learning methods for TSF, their capacity to predict long-term series remains constrained. This limitation arises from the failure to account for both intra- and inter-variable variations meanwhile. To mitigate this challenge, we introduce the Fi$^2$VBlock, which leverages a \textbf{F}requency domain perspective to capture \textbf{i}ntra- and \textbf{i}nter-variable \textbf{V}ariations. After transforming into the frequency domain via the Frequency Transform Module, the Frequency Cross Attention between the real and imaginary parts is designed to obtain enhanced frequency representations and capture intra-variable variations. Furthermore, Inception blocks are employed to integrate information, thus capturing correlations across different variables. Our backbone network, Fi$^2$VTS, employs a residual architecture by concatenating multiple Fi$^2$VBlocks, thereby preventing degradation issues. Theoretically, we demonstrate that Fi$^2$VTS achieves a substantial reduction in both time and memory complexity, decreasing from $\mathcal{O}(L^2)$ to $\mathcal{O}(L)$ per Fi$^2$VBlock computation. Empirical evaluations reveal that Fi$^2$VTS outperforms other baselines on two benchmark datasets. The implementation code is accessible at \url{https://github.com/HITshenrj/Fi2VTS}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21275 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fi$^2$VTS: Time Series Forecasting Via Capturing Intra- and Inter-Variable Variations in the Frequency Domain Shen, Rujia Yang, Yang Lin, Yaoxion Liu, Liangliang Wang, Boran Guan, Yi Jiang, Jingchi Artificial Intelligence Time series forecasting (TSF) plays a crucial role in various applications, including medical monitoring and crop growth. Despite the advancements in deep learning methods for TSF, their capacity to predict long-term series remains constrained. This limitation arises from the failure to account for both intra- and inter-variable variations meanwhile. To mitigate this challenge, we introduce the Fi$^2$VBlock, which leverages a \textbf{F}requency domain perspective to capture \textbf{i}ntra- and \textbf{i}nter-variable \textbf{V}ariations. After transforming into the frequency domain via the Frequency Transform Module, the Frequency Cross Attention between the real and imaginary parts is designed to obtain enhanced frequency representations and capture intra-variable variations. Furthermore, Inception blocks are employed to integrate information, thus capturing correlations across different variables. Our backbone network, Fi$^2$VTS, employs a residual architecture by concatenating multiple Fi$^2$VBlocks, thereby preventing degradation issues. Theoretically, we demonstrate that Fi$^2$VTS achieves a substantial reduction in both time and memory complexity, decreasing from $\mathcal{O}(L^2)$ to $\mathcal{O}(L)$ per Fi$^2$VBlock computation. Empirical evaluations reveal that Fi$^2$VTS outperforms other baselines on two benchmark datasets. The implementation code is accessible at \url{https://github.com/HITshenrj/Fi2VTS}. |
| title | Fi$^2$VTS: Time Series Forecasting Via Capturing Intra- and Inter-Variable Variations in the Frequency Domain |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2407.21275 |