TA-SparseMG extends SparseTSF with trend-aware reversible instance normalization, scale-adaptive gated denoising, and multiscale gated-attention MLP modules to achieve superior performance on long-term time series forecasting benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TA-SparseMG: Trend-Aware Sparse Forecasting via Multi-Scale Gating for Long-Term Time Series
TA-SparseMG extends SparseTSF with trend-aware reversible instance normalization, scale-adaptive gated denoising, and multiscale gated-attention MLP modules to achieve superior performance on long-term time series forecasting benchmarks.