arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.13041cs.LG
收藏

TimeFilter:面向时间序列预测的分块特定时空图过滤方法

TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting

Fudan University(复旦大学);Tongji University(同济大学);Griffith University(格里菲斯大学)

Yifan Hu, Guibin Zhang, Peiyuan Liu, Disen Lan, Naiqi Li, Dawei Cheng, Tao Dai, Shu-Tao Xia, Shirui Pan

AI总结:

针对现有时间序列预测通道依赖建模存在噪声、粗粒度聚类难以捕获复杂时变交互的问题,提出基于GNN的TimeFilter框架,通过分块特定的时空图过滤保留关键关联,在13个多领域真实数据集上实现SOTA性能。

摘要:

时间序列预测方法主要分为两类:通道独立(Channel Independent, CI)策略和通道依赖(Channel Dependent, CD)策略。CI策略忽略了重要的协变量关系,而CD策略不加区分地捕获所有依赖关系,会引入噪声并降低泛化能力。近期通道聚类(Channel Clustering, CC)领域的进展旨在通过将特征相似的通道分组、采用定制化建模技术来优化依赖关系建模,但粗粒度聚类难以有效捕获复杂的时变交互关系。为解决这些挑战,我们提出TimeFilter,这是一种基于图神经网络(GNN)的自适应细粒度依赖建模框架。在根据输入序列构建图后,TimeFilter会过滤掉不相关的关联,同时以分块特定的方式保留最关键的关联,以此优化学习到的时空依赖关系。我们在来自不同应用领域的13个真实数据集上开展了大量实验,结果证明TimeFilter取得了当前最优性能。代码可在https://github.com/TROUBADOUR000/TimeFilter获取。

英文摘要:

Time series forecasting methods generally fall into two main categories: Channel Independent (CI) and Channel Dependent (CD) strategies. While CI overlooks important covariate relationships, CD captures all dependencies without distinction, introducing noise and reducing generalization. Recent advances in Channel Clustering (CC) aim to refine dependency modeling by grouping channels with similar characteristics and applying tailored modeling techniques. However, coarse-grained clustering struggles to capture complex, time-varying interactions effectively. To address these challenges, we propose TimeFilter, a GNN-based framework for adaptive and fine-grained dependency modeling. After constructing the graph from the input sequence, TimeFilter refines the learned spatial-temporal dependencies by filtering out irrelevant correlations while preserving the most critical ones in a patch-specific manner. Extensive experiments on 13 real-world datasets from diverse application domains demonstrate the state-of-the-art performance of TimeFilter. The code is available at https://github.com/TROUBADOUR000/TimeFilter.

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。

↑