TA-SparseMG: Trend-Aware Sparse Forecasting via Multi-Scale Gating for Long-Term Time Series

2026-06-26

AI Summary

This work addresses the challenge that lightweight models often struggle to balance parameter efficiency and predictive performance in long-term time series forecasting, primarily due to non-stationarity, high-frequency perturbations, and cross-period dependencies. Building upon the SparseTSF framework, the paper introduces three key innovations: trend-aware reversible instance normalization to mitigate distributional shifts, scale-adaptive gated denoising to suppress high-frequency noise, and a multi-scale gated attention MLP to enhance modeling of cross-period features. Extensive experiments demonstrate that the proposed method achieves consistently superior forecasting accuracy across multiple benchmarks. Ablation studies further confirm that each component effectively improves distribution adaptability, input robustness, and cross-period representational capacity, respectively.

Abstract

Long-term time series forecasting finds extensive applications in domains such as power demand, traffic flow, meteorological observation, and renewable energy dispatch. Forecasting dynamically varying long-term time series poses inherent challenges, including statistical nonstationarity, local high-frequency disturbances, and coupled cross-period dependencies, which make it difficult for lightweight models to balance parameter efficiency and forecasting performance. To address this issue, this study presents TA-SparseMG, a lightweight cross-period forecasting model built on SparseTSF's sparse cross-period modeling framework. It incorporates three key modules: a trend-aware reversible instance normalization module, a scale-adaptive gated denoising module, and a multiscale gated-attention MLP forecasting module. The trend-aware normalization module captures input-window statistics and calibrates forecast-window distributions, effectively mitigating distribution shift. The scale-adaptive gated denoising module performs feature smoothing and residual suppression before period rearrangement, thereby reducing interference from high-frequency perturbations. The multiscale gated attention prediction module strengthens the prediction head's adaptive representational capacity via conditional gating and feature modulation. Extensive experiments across multiple LTSF benchmarks demonstrate that the proposed TA-SparseMG consistently achieves superior, stable performance. Ablation studies confirm that each module independently improves distribution adaptation, input robustness, and cross-period feature mapping capability.

Problem

• long-term time series forecasting
• statistical nonstationarity
• high-frequency disturbances
• cross-period dependencies
• parameter efficiency

Innovation

• trend-aware normalization
• scale-adaptive denoising
• multiscale gated attention
• sparse cross-period modeling
• lightweight forecasting