Parameter-Efficient Temporal Convolutional Networks for Multivariate Time-Series Forecasting
AI · 12.11.2026 · 7 (11) · 481
DOI: 10.3390/ai7110481 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI, online erschienen am 12.11.2026. Verfasst von Aleksa Bogdanović und 3 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Science, Technological Development and Innovation of the Republic of Serbia, Innovation of the Republic of Serbia through the Mathematical Institute SANU, University of Niš, Faculty of Electronic Engineering.
Abstract (Originalsprache)
Accurate prediction of multivariate datasets increasingly relies on deep learning models, often increasing complexity and computing requirements, particularly for multi-horizon predictions. This work proposes a model designed to significantly reduce computing requirements while retaining predictive accuracy. By replacing standard convolutions with depthwise and grouped pointwise operations, the model preserves temporal processing and captures dependencies without substantially complicating the architecture. Evaluated on five multivariate datasets across four forecasting horizons, the proposed model is compared against conventional and depthwise Temporal Convolutional Networks; lightweight variants, such as TSMixer and FITS; and advanced models like Informer, Autoformer, and iTransformer. It reduces multiply–accumulate operations by 58.9–70.8% and trainable parameters by 14.15–35.8% compared to standard temporal convolution networks. Notably, forecasting accuracy varies across datasets and horizons, with small differences between TCN variants corresponding to run-to-run variability. The findings reveal that the model excels in accuracy–efficiency trade-offs, offering an alternative for multivariate time-series forecasting when computational cost is a critical consideration.
Förderung
- Ministry of Science, Technological Development and Innovation of the Republic of Serbia
- Innovation of the Republic of Serbia through the Mathematical Institute SANU
- University of Niš, Faculty of Electronic Engineering
Zitieren
APA
Bogdanović, A., Velimirović, L. Z., Velimirović, J. D., & Stajić, Z. (2026). Parameter-Efficient Temporal Convolutional Networks for Multivariate Time-Series Forecasting. AI, 7(11), 481. https://doi.org/10.3390/ai7110481
Vancouver
Bogdanović A, Velimirović LZ, Velimirović JD, Stajić Z. Parameter-Efficient Temporal Convolutional Networks for Multivariate Time-Series Forecasting. AI. 2026;7(11):481. doi:10.3390/ai7110481
BibTeX
@article{Bogdanovi2026,
author = {Bogdanović, Aleksa and Velimirović, Lazar Z. and Velimirović, Jelena D. and Stajić, Zoran},
title = {Parameter-Efficient Temporal Convolutional Networks for Multivariate Time-Series Forecasting},
journal = {AI},
year = {2026},
volume = {7},
number = {11},
pages = {481},
doi = {10.3390/ai7110481}
}
EUVIMED