Rethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning

Zhiquan Huang; Jiazhe Wang; Linjing Xue; Ming Liu; Meiwen Li; Ruijuan Zheng

cs.AIAug 20, 2026

Rethinking Patch Based Multivariate Time Series Forecasting with Semantic Structured Partitioning

Authors: Zhiquan Huang, Jiazhe Wang, Linjing Xue, Ming Liu, Meiwen Li, Ruijuan Zheng

Organizations: School of Information Engineering, Henan University of Science and Technology, Luoyang, 471023, Henan, China · School of Software, Henan University of Science and Technology, Luoyang, 471000, Henan, China

Abstract

Multivariate time series forecasting (MTSF) is a fundamental task in many real world applications. Existing patch based forecasting methods generally fall into three categories: fixed partitioning, multi-scale partitioning, and extendable partitioning. Fixed partitioning often breaks meaningful temporal boundaries, multi-scale partitioning may introduce redundant representations across scales, and extendable partitioning improves flexibility but still lacks an explicit mechanism for organizing semantic structure and modeling interactions among heterogeneous temporal patterns. To address these limitations, we propose SCPaT, a Transformer based framework built on semantic structured partitioning. SCPaT first decomposes input sequences into semantically consistent units through adaptive semantic unit generation, then constructs a dynamic semantic graph to model directed dependencies among these units and organize them into higher order semantic blocks. Based on these structured representations, an importance aware routing mechanism adaptively dispatches different semantic blocks to different experts for customized modeling. Extensive experiments on 12 real world datasets demonstrate the effectiveness of SCPaT.

Figures & tables

Figure 1 : Comparison of four patch based schemes: fixed partitioning, multi-scale partitioning, extendable partitioning, and the proposed semantic structured partitioning.

Figure 2 : SCPaT architecture consists of: (a) Semantic Vector Encoder, which encodes time series into semantic units; (b) Transfer Entropy Graph Constructor, quantifies directed dependencies and constructs a dynamic semantic graph; and (c) Importance aware Routing, allocates customized processing strategies to different semantic blocks for effective modeling.

Task Type	Dataset	Prediction Horizons	Time Point	Dimension	Frequency
Long-term Forecasting	ETTh1	{96,192,336,720}	17420	7	Hourly
	ETTh2	{96,192,336,720}	17420	7	Hourly
	ETTm1	{96,192,336,720}	69680	7	15 min
	ETTm2	{96,192,336,720}	69680	7	15 min
	Weather	{96,192,336,720}	52603	21	10 min
	Traffic	{96,192,336,720}	17451	862	Hourly

Table 1 : Summary of the 12 datasets used in our forecasting experiments, including the prediction horizons, data dimensionality, sampling frequency, and total number of time points.

Models		SCPaT ( Ours )		MSPatch		DUET		iTransformer		MSGNet		HDMixer		PatchTST		TimesNet		CrossFormer
Metric		MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE
ETTh1	96	0.370	0.392	0.372	0.395	0.384	0.402	0.386	0.405	0.390	0.411	0.386	0.401	0.414	0.419	0.384	0.402	0.423	0.448
	192	0.418	0.422	0.428	0.426	0.437	0.429	0.441	0.436	0.442	0.442	0.441	0.430	0.460	0.445	0.446	0.439	0.471	0.474
	336	0.452	0.440	0.484	0.452	0.477	0.453	0.465	0.445	0.487	0.458	0.458	0.443	0.501	0.466	0.491	0.469	0.570	0.546
	720	0.449	0.458	0.480	0.473	0.486	0.475	0.503	0.491	0.494	0.488	0.512	0.484	0.500	0.488	0.521	0.500	0.653	0.621
ETTh2	96	0.288	0.338	0.292	0.344	0.298	0.351	0.297	0.349	0.328	0.371	0.293	0.338	0.302	0.348	0.340	0.374	0.745	0.584

Table 2 : Multivariate long-term forecasting results over four prediction horizons,

H\in\{96,192,336,720\}

, with the input length fixed at

L=96

. The best and second-best results are marked in bold red and blue underline , respectively.

Models		SCPaT ( Ours )		MSPatch		DUET		iTransformer		MSGNet		HDMixer		TimesNet		PatchTST		CrossFormer
Metric		MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE
PEMS03	12	0.066	0.169	0.074	0.179	0.071	0.176	0.071	0.174	0.083	0.197	0.076	0.184	0.085	0.192	0.099	0.216	0.090	0.203
	24	0.086	0.195	0.097	0.200	0.089	0.197	0.093	0.201	0.097	0.217	0.095	0.210	0.118	0.223	0.142	0.259	0.121	0.240
	48	0.122	0.235	0.131	0.244	0.118	0.229	0.125	0.236	0.135	0.241	0.122	0.245	0.155	0.260	0.211	0.319	0.202	0.317
PEMS04	12	0.073	0.176	0.075	0.185	0.076	0.179	0.078	0.183	0.082	0.187	0.084	0.188	0.087	0.195	0.105	0.224	0.098	0.218
	24	0.091	0.199	0.093	0.201	0.097	0.203	0.095	0.205	0.128	0.241	0.097	0.210	0.103	0.215	0.153	0.257	0.131	0.256

Table 3 : Multivariate short-term forecasting results over three prediction horizons,

H\in\{12,24,48\}

, with the input length fixed at

L=96

. The best and second-best results are marked in bold red and blue underline , respectively.

Figure 3 : Sensitivity analysis of the hyperparameters

\alpha

and Top-P on ETTm1, ETTh1, ETTh2, and Weather, with both the input length and prediction horizon fixed at 96.

Dataset	Expert 1	Expert 2	Expert 3
ETTh1	0.62	0.21	0.17
ETTm1	0.51	0.25	0.24
Weather	0.81	0.11	0.08

Table 4 : Average routing probability distribution across experts, with both the input length and prediction horizon fixed at 96.

Figure 4 : Performance degradation under different Gaussian noise levels on ETTh1 and Weather with both the input length and prediction horizon fixed at 96.

Figure 5 : Performance comparison under different look-back window lengths on ETTm1, ETTh1, Electricity, and Weather, with

L\in\{48,96,192,336,720\}

and the prediction horizon fixed at 96.

Missing Rate	ETTm2						ETTh1
	SCPaT (Ours)		iTransformer		PatchTST		SCPaT (Ours)		iTransformer		PatchTST
	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE	MSE	MAE
0.00	0.173	0.258	0.180	0.264	0.181	0.259	0.370	0.392	0.386	0.405	0.414	0.419
0.05	0.213	0.297	0.249	0.441	0.252	0.327	0.379	0.401	0.404	0.413	0.436	0.428
0.10	0.248	0.326	0.295	0.472	0.328	0.376	0.390	0.412	0.433	0.424	0.455	0.441
0.15	0.287	0.354	0.379	0.559	0.411	0.423	0.404	0.424	0.462	0.432	0.467	0.460

Table 5 : Robustness analysis on the ETTm2 and ETTh1 datasets under different missing rates, with the input length fixed at

L=96

and the prediction horizon fixed at

H=96

. The best results are highlighted in bold.

Figure 6 : Heatmaps of the learned directed adjacency matrix $A_{\text{final}}$ on the ETTh1 and Weather datasets.

Figure 7 : Visualization of prediction results on Electricity, Traffic, and ETTh2 under the Lookback-96-Horizon-96 setting.

Dataset		ETTm2				Weather				Traffic
Prediction Length		96	192	336	720	96	192	336	720	96	192	336	720
SCPaT	MSE	0.173	0.238	0.297	0.394	0.163	0.209	0.266	0.345	0.393	0.425	0.454	0.489
SCPaT	MAE	0.258	0.300	0.339	0.394	0.208	0.250	0.292	0.349	0.247	0.259	0.270	0.291
w/o SV Encoder	MSE	0.196	0.259	0.317	0.412	0.204	0.248	0.302	0.373	0.414	0.448	0.478	0.510
w/o SV Encoder	MAE	0.278	0.318	0.354	0.408	0.254	0.287	0.323	0.367	0.274	0.281	0.294	0.316
w/o IAR	MSE	0.178	0.245	0.302	0.400	0.167	0.216	0.273	0.353	0.397	0.431	0.459	0.495

Table 6 : Ablation results of the SCPaT components on ETTm2, Weather, and Traffic over prediction horizons

H\in\{96,192,336,720\}

, with the input length fixed at

L=96

. The best and second-best results are marked in bold red and blue underline , respectively.

Figure 8 : Model efficiency comparison of different methods on ETTm2 and Weather.

Explore similar work

DMSC: Dynamic Multi-Scale Coordination Framework for Time Series Forecasting
Aug 3, 2025Haonan Yang, Jianchao Tang, Zhuo Li +1Multi-Scale Convolution Multiscale
National University of Defense Technology, Changsha, Hunan, China
NPMixer: Hierarchical Neighboring Patch Mixing for Time Series Forecasting
May 8, 2026Jung Min Choi, Vijaya Krishna Yalavarthi, Lars Schmidt-ThiemeMultivariate Time Series Forecasting Time Series Forecasting
1ISMLL, University of Hildesheim, VWFS Data Analytics Research Center (VWFS-DARC), Hildesheim, Germany.
A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting
Sep 19, 2026Li Lin, Zhihao Lin, Qi Zhang +3Time Series Foundation Models
Southeast University, China · Nanyang Technological University, Singapore · Timecho Ltd., China

Aug 3, 2025, cs.LGJ/K move · Enter open · S save

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

Haonan Yang, Jianchao Tang, Zhuo Li, Long Lan

National University of Defense Technology, Changsha, Hunan, China

Multi-Scale Convolution Multiscale Temporal Dependence Adaptive Coordination

Open paper AskPDF arXiv

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.

Abstract

Explore similar work

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

NPMixer: Hierarchical Neighboring Patch Mixing for Time Series Forecasting

A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting