Scholarlink

<p>Multivariate time series (MTS) forecasting involves the use of multiple interrelated sequential data to predict future trends, necessitating the extraction of potential associative information from complex historical data. Currently, Transformers dominate the field of MTS prediction due to their core mechanism of self-attention, which effectively captures long-range dependencies. However, self-attention is inherently permutation-invariant, leading to the loss of sequential information. To address this issue, we propose the Dual-Branch Temporal Feature Fusion Network with Fast GRU (DBFF-GRU). In the feature fusion module, a dual-branch convolutional structure is employed to extract local and global features from the time series data separately, and a lightweight attention module is integrated into the global feature branch to capture dependencies among variables. Additionally, we introduce a fast iterative GRU structure to further capture long-term dependencies and enhance model efficiency. Extensive experiments on real-world data demonstrate the effectiveness of DBFF-GRU compared to state-of-the-art techniques.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

DBFF-GRU: dual-branch temporal feature fusion network with fast GRU for multivariate time series forecasting

  • 期刊论文

  • 发表日期：

    2025年4月3日

查看全文
  • Jinglei Li,
  • Dongsheng Liu,
  • Guofang Ma,
  • Yaning Chen,
  • Hongwei Jiang

摘要

Multivariate time series (MTS) forecasting involves the use of multiple interrelated sequential data to predict future trends, necessitating the extraction of potential associative information from complex historical data. Currently, Transformers dominate the field of MTS prediction due to their core mechanism of self-attention, which effectively captures long-range dependencies. However, self-attention is inherently permutation-invariant, leading to the loss of sequential information. To address this issue, we propose the Dual-Branch Temporal Feature Fusion Network with Fast GRU (DBFF-GRU). In the feature fusion module, a dual-branch convolutional structure is employed to extract local and global features from the time series data separately, and a lightweight attention module is integrated into the global feature branch to capture dependencies among variables. Additionally, we introduce a fast iterative GRU structure to further capture long-term dependencies and enhance model efficiency. Extensive experiments on real-world data demonstrate the effectiveness of DBFF-GRU compared to state-of-the-art techniques.