HTRNet: Hierarchical Temporal-Relation Refinement Network for Multivariate Time Series Forecasting
Electronics · 2026-11-15 · 15 (22) · 5307
DOI: 10.3390/electronics15225307 ↗At a glance
Journal article in Electronics, published online on 2026-11-15. Written by Changzhi Lv and 4 co-authors. 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, National Key Research and Development Program of China, Key Research and Development Program of Shandong Province.
Abstract (original language)
Multivariate time series forecasting requires modeling both variable-specific temporal patterns and inter-variable relations, including dependencies shared across samples and interactions that vary with the input. In this paper, we propose a Hierarchical Temporal-Relation Refinement Network (HTRNet) for multivariate time series forecasting. HTRNet sequentially learns variable-specific latent representations and models inter-variable relations from the resulting residuals within each refinement layer. The framework supports both single-layer and multi-layer configurations; when multiple layers are used, the updated residual representations are propagated to subsequent layers for further refinement. In addition, a Learnable Static Relation Matrix (LSRM) learns sample-independent relation weights among variables, while a Dynamic Compensation Module (DCM) uses sample-specific inter-variable interactions to enhance the final residual representation and generate a compensation prediction. The final forecast combines the layer-wise predictions with the DCM output. Extensive experiments are conducted on widely used benchmark datasets, including ETT, Weather, Electricity, Traffic, and Solar-Energy, across multiple forecasting horizons. Averaging the relative reductions against the best baseline for each dataset and metric yields improvements of 2.01% in MSE and 4.83% in MAE. These gains vary across datasets and forecasting horizons. On Traffic, HTRNet achieves the lowest average MAE but has a higher average MSE than DeepBooTS, iTransformer, and CASA.
Funding
- National Natural Science Foundation of China
- National Key Research and Development Program of China
- Key Research and Development Program of Shandong Province
- Key Technology Research and Industrialization Demonstration Project of Qingdao
Cite
APA
Lv, C., Li, Z., Wang, X., Fan, D., & Xin, D. (2026). HTRNet: Hierarchical Temporal-Relation Refinement Network for Multivariate Time Series Forecasting. Electronics, 15(22), 5307. https://doi.org/10.3390/electronics15225307
Vancouver
Lv C, Li Z, Wang X, Fan D, Xin D. HTRNet: Hierarchical Temporal-Relation Refinement Network for Multivariate Time Series Forecasting. Electronics. 2026;15(22):5307. doi:10.3390/electronics15225307
BibTeX
@article{Lv2026,
author = {Lv, Changzhi and Li, Zichao and Wang, Xuefeng and Fan, Di and Xin, Dongjin},
title = {HTRNet: Hierarchical Temporal-Relation Refinement Network for Multivariate Time Series Forecasting},
journal = {Electronics},
year = {2026},
volume = {15},
number = {22},
pages = {5307},
doi = {10.3390/electronics15225307}
}
EUVIMED