Scholarlink

<p>The use of traditional deep learning models for time series forecasting has demonstrated strong performance in specific domains, but their applicability remains limited due to their domain-specific nature, which restricts generalization. Inspired by advancements in natural language processing (NLP) and computer vision (CV), large language models (LLMs) have emerged as a promising method for time series forecasting. However, fundamental differences between time series data and textual data present challenges in adapting time series for LLM-based forecasting. To address this, we propose an <b>I</b>nteger-<b>D</b>ecimal <b>D</b>ecomposition and cross-modal fine-tuning framework for <b>LLM</b>s (IDDLLM). Our approach designs the <b>S</b>plitting time series <b>D</b>ata <b>C</b>ross-attention (SDC) module, which decomposes time series data into integer and decimal components, enabling better correlation analysis and improving the model’s understanding of time series patterns. Additionally, we design a dual cross-attention module to align time series modalities and text modalities, facilitating more effective adaptation of time series within LLMs. Comprehensive evaluations demonstrate that IDDLLM outperforms state-of-the-art models in long-term time series forecasting, ranking first in 34 out of 46 experimental settings and second in 9 settings. Furthermore, it achieves competitive performance in few-shot and zero-shot forecasting tasks, highlighting its robustness and adaptability.</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

A novel LLM time series forecasting method based on integer-decimal decomposition

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月2日

查看全文
  • Lei Wang,
  • Keyao Dong,
  • Xiaoyong Zhao

摘要

The use of traditional deep learning models for time series forecasting has demonstrated strong performance in specific domains, but their applicability remains limited due to their domain-specific nature, which restricts generalization. Inspired by advancements in natural language processing (NLP) and computer vision (CV), large language models (LLMs) have emerged as a promising method for time series forecasting. However, fundamental differences between time series data and textual data present challenges in adapting time series for LLM-based forecasting. To address this, we propose an Integer-Decimal Decomposition and cross-modal fine-tuning framework for LLMs (IDDLLM). Our approach designs the Splitting time series Data Cross-attention (SDC) module, which decomposes time series data into integer and decimal components, enabling better correlation analysis and improving the model’s understanding of time series patterns. Additionally, we design a dual cross-attention module to align time series modalities and text modalities, facilitating more effective adaptation of time series within LLMs. Comprehensive evaluations demonstrate that IDDLLM outperforms state-of-the-art models in long-term time series forecasting, ranking first in 34 out of 46 experimental settings and second in 9 settings. Furthermore, it achieves competitive performance in few-shot and zero-shot forecasting tasks, highlighting its robustness and adaptability.