TimeFilter improves multivariate time series forecasting by dynamically filtering a patch-level spatial-temporal graph with a Mixture-of-Experts router, achieving state-of-the-art MSE on 13 benchmarks.
The input length L is searched from {192, 336, 512, 720} for optimal horizon in the scaling law of TSF (Shi et al., 2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TimeFilter: Patch-Specific Spatial-Temporal Graph Filtration for Time Series Forecasting
TimeFilter improves multivariate time series forecasting by dynamically filtering a patch-level spatial-temporal graph with a Mixture-of-Experts router, achieving state-of-the-art MSE on 13 benchmarks.