Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

DMSC: Dynamic Multi-Scale Coordination Framework for Time Series Forecasting

About

Time Series Forecasting (TSF) faces persistent challenges in modeling intricate temporal dependencies across different scales. Despite recent advances leveraging different decomposition operations and novel architectures based on CNN, MLP or Transformer, existing methods still struggle with static decomposition strategies, fragmented dependency modeling, and inflexible fusion mechanisms, limiting their ability to model intricate temporal dependencies. To explicitly solve the mentioned three problems respectively, we propose a novel Dynamic Multi-Scale Coordination Framework (DMSC) with Multi-Scale Patch Decomposition block (EMPD), Triad Interaction Block (TIB) and Adaptive Scale Routing MoE block (ASR-MoE). Specifically, EMPD is designed as a built-in component to dynamically segment sequences into hierarchical patches with exponentially scaled granularities, eliminating predefined scale constraints through input-adaptive patch adjustment. TIB then jointly models intra-patch, inter-patch, and cross-variable dependencies within each layer's decomposed representations. EMPD and TIB are jointly integrated into layers forming a multi-layer progressive cascade architecture, where coarse-grained representations from earlier layers adaptively guide fine-grained feature extraction in subsequent layers via gated pathways. And ASR-MoE dynamically fuses multi-scale predictions by leveraging specialized global and local experts with temporal-aware weighting. Comprehensive experiments on thirteen real-world benchmarks demonstrate that DMSC consistently maintains state-of-the-art (SOTA) performance and superior computational efficiency for TSF tasks. Code is available at https://github.com/1327679995/DMSC.

Haonan Yang, Jianchao Tang, Zhuo Li, Long Lan• 2025

Related benchmarks

TaskDatasetResultRank
Long-term time-series forecastingETTh1
MAE0.395
600
Long-term forecastingETTh1
MSE0.372
500
Long-term time-series forecastingETTh2
MSE0.355
474
Long-term time-series forecastingTraffic
MSE0.389
433
Short-term forecastingPeMS03
MAE0.171
146
Short-term forecastingPeMS07
MAE0.193
99
Short-term forecastingPeMS08
MSE0.162
95
Short-term forecastingPeMS04
MSE0.129
95
Long-term forecastingsolar
MSE0.191
70
Long-term time-series forecastingsolar
MSE0.226
69
Showing 10 of 12 rows

Other info

Follow for update