arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2512.00293cs.LGcs.AI
收藏

FiCoTS: 细到粗的LLM增强层次跨模态交互用于时间序列预测

FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting

School of Advanced Interdisciplinary Sciences, University of Chinese Academy Sciences(中国科学院大学先进交叉学科学院);MAIS, Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所MAIS);Great Bay University(大亚大学)

Yafei Lyu, Hao Zhou, Lu Zhang, Xu Yang, Zhiyong Liu

AI总结:

FiCoTS通过细到粗的LLM增强层次跨模态交互框架,提升多模态时间序列预测的性能。

摘要:

时间序列预测是数据分析和网络技术的核心。最近大型语言模型(LLM)的成功为这一领域提供了巨大的潜力,尤其是在跨模态方面。大多数方法采用LLM作为预测器的范式,使用LLM作为预测骨干,并设计模态对齐机制,使LLM能够理解时间序列数据。然而,时间序列和文本的两种模态的语义信息差异显著,使LLM难以完全理解时间序列数据。为缓解这一挑战,我们的工作遵循LLM作为增强器的范式,充分利用LLM在文本理解方面的优势,其中LLM仅用于编码文本模态以补充时间序列模态。基于这一范式,我们提出了FiCoTS,一种LLM增强的细到粗框架,用于多模态时间序列预测。具体而言,该框架通过细到粗的三个层次促进渐进的跨模态交互:首先,在token级模态对齐模块中,构建了一个动态异构图以过滤噪声并将时间序列片段与文本token对齐;其次,在特征级模态交互模块中,引入了全局跨注意力机制,使每个时间序列变量能够连接到相关的文本上下文;第三,在决策级模态融合模块中,我们设计了一个门控网络,以适应性地融合两种模态的结果以实现稳健的预测。这三个模块协同工作,使两种模态在三个语义层次上全面交互,使文本信息能够有效支持时间预测。在七个现实世界基准上的大量实验表明,我们的模型实现了最先进的性能。代码将公开发布。

英文摘要:

Time series forecasting is central to data analysis and web technologies. The recent success of Large Language Models (LLMs) offers significant potential for this field, especially from the cross-modality aspect. Most methods adopt an LLM-as-Predictor paradigm, using LLM as the forecasting backbone and designing modality alignment mechanisms to enable LLM to understand time series data. However, the semantic information in the two modalities of time series and text differs significantly, making it challenging for LLM to fully understand time series data. To mitigate this challenge, our work follows an LLM-as-Enhancer paradigm to fully utilize the advantage of LLM in text understanding, where LLM is only used to encode text modality to complement time series modality. Based on this paradigm, we propose FiCoTS, an LLM-enhanced fine-to-coarse framework for multimodal time series forecasting. Specifically, the framework facilitates progressive cross-modality interaction by three levels in a fine-to-coarse scheme: First, in the token-level modality alignment module, a dynamic heterogeneous graph is constructed to filter noise and align time series patches with text tokens; Second, in the feature-level modality interaction module, a global cross-attention mechanism is introduced to enable each time series variable to connect with relevant textual contexts; Third, in the decision-level modality fusion module, we design a gated network to adaptively fuse the results of the two modalities for robust predictions. These three modules work synergistically to let the two modalities interact comprehensively across three semantic levels, enabling textual information to effectively support temporal prediction. Extensive experiments on seven real-world benchmarks demonstrate that our model achieves state-of-the-art performance. The codes will be released publicly.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑