同济大学同济大学 数字经济研究中心网络金融安全(国家级)协同创新中心

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

TimeFilter 整体结构
TimeFilter 整体结构

内容概括

时间序列预测中,通道独立策略忽略变量间的关联,通道依赖策略不加区分地建模全部依赖、容易引入噪声,按特征相似性分组的通道聚类又难以刻画复杂、随时间变化的交互。TimeFilter 是基于图神经网络的依赖建模框架:先由输入序列构建时空图,再以 patch 为单位过滤无关关联、保留最关键的依赖,实现自适应、细粒度的依赖建模。论文在 13 个来自不同应用领域的真实数据集上进行了实验。

原文摘要

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.

相关资源

来源:ICML 2025 · 原文摘要

返回论文发表