TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
This addresses the challenge of noisy and generalized dependency modeling in time series forecasting, offering an incremental improvement over existing channel clustering methods.
The paper tackles the problem of modeling dependencies in time series forecasting by proposing TimeFilter, a GNN-based framework that adaptively filters irrelevant correlations in a patch-specific manner, achieving state-of-the-art performance on 13 real-world datasets.
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.