Re-uploading Data in Tensor Network
Electronics and Control Systems · 29.09.2025 · 3 (85) · 27-33
DOI: 10.18372/1990-5548.85.20428 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics and Control Systems, online erschienen am 29.09.2025. Verfasst von Victor Sineglazov und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
In this paper, we present an approach for enhancing quantum tensor networks through the method of data re-uploading. The proposed framework integrates multiple layers of classical data encoding into tensor network architectures, thereby improving their approximation capacity and reducing the impact of barren plateaus in training. The model construction relies on tree tensor networks combined with RX, RZ, and RY rotational gates and CNOT entanglement, while optimization is performed using differential evolution as a gradient-free algorithm. Experimental evaluation was carried out on the iris and wine datasets, comparing baseline tensor networks with architectures incorporating one to three re-uploading layers. The results demonstrate a consistent reduction in training and test loss, with accuracy, recall, and precision reaching 100% on the iris dataset for three layers and improvements of up to 40% in prediction quality on the wine dataset. These findings confirm that data re-uploading significantly enhances the performance and expressiveness of tensor network-based quantum models.
Zitieren
APA
Sineglazov, V., & Chynnyk, P. (2025). Re-uploading Data in Tensor Network. Electronics and Control Systems, 3(85), 27-33. https://doi.org/10.18372/1990-5548.85.20428
Vancouver
Sineglazov V, Chynnyk P. Re-uploading Data in Tensor Network. Electronics and Control Systems. 2025;3(85):27-33. doi:10.18372/1990-5548.85.20428
BibTeX
@article{Sineglazov2025,
author = {Sineglazov, Victor and Chynnyk, Petro},
title = {Re-uploading Data in Tensor Network},
journal = {Electronics and Control Systems},
year = {2025},
volume = {3},
number = {85},
pages = {27--33},
doi = {10.18372/1990-5548.85.20428}
}
EUVIMED