Scholarlink

<p>Although Transformer-based models have achieved good performance in time series forecasting, existing methods still have limitations in modeling long-term dependencies. To this end, we propose a retrieval-augmented framework for time series forecasting, which models the long-range dependency explicitly. First, we consider both time-domain and frequency-domain similarities to retrieve top-<i>K</i> similar historical sequences for each input sequence. Subsequently, to fully exploit the retrieved information while suppressing potential noise, a dual-branch architecture is designed: the original sequence branch primarily models the internal dependencies of the current input, while the retrieval-augmented branch models the relationship between the current input and the retrieved historical sequences through a cross-attention mechanism. Furthermore, to adaptively balance the contributions of the two branches, a gating fusion mechanism is introduced to dynamically adjust the proportion of information integration from the two branches. Experiments on several public datasets show that our proposed method achieves superior and stable performance compared to existing methods, especially in long-term forecasting settings.</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

Retrieval-Augmented Framework with Adaptive Gating for Time Series Forecasting

  • 期刊论文

  • 发表日期：

    2025年9月5日

查看全文
  • Yiqiao Wang,
  • Pengfei Wang,
  • Xiaotian Gu,
  • Xiaoling Wang

摘要

Although Transformer-based models have achieved good performance in time series forecasting, existing methods still have limitations in modeling long-term dependencies. To this end, we propose a retrieval-augmented framework for time series forecasting, which models the long-range dependency explicitly. First, we consider both time-domain and frequency-domain similarities to retrieve top-K similar historical sequences for each input sequence. Subsequently, to fully exploit the retrieved information while suppressing potential noise, a dual-branch architecture is designed: the original sequence branch primarily models the internal dependencies of the current input, while the retrieval-augmented branch models the relationship between the current input and the retrieved historical sequences through a cross-attention mechanism. Furthermore, to adaptively balance the contributions of the two branches, a gating fusion mechanism is introduced to dynamically adjust the proportion of information integration from the two branches. Experiments on several public datasets show that our proposed method achieves superior and stable performance compared to existing methods, especially in long-term forecasting settings.