EUVIMEDEUVIMED entdecken
Crossref

Empowering Tensor Network Decompositions by Nonlinear and Incompatible Tensor Contraction

Sheng Liu, Xi-Le Zhao, Qin Jiang, Michael K. Ng

SIAM Journal on Imaging Sciences · 31.12.2026 · 19 (4) · 2479-2511

DOI: 10.1137/25m182669x ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Imaging Sciences, online erschienen am 09.11.2026. Verfasst von Sheng Liu und 3 weiteren Autor:innen. Die Arbeit nennt 63 Literaturangaben. Gefördert von: National Key R&D Program of China, Sichuan Science and Technology Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, tensor network decompositions have become powerful tools in imaging science for representing high-dimensional images, with tensor contraction serving as a fundamental interaction between tensor factors. However, the potential of classical tensor contraction is limited by its linear and dimension-compatible nature. To break this limitation, we propose a nonlinear and incompatible tensor contraction as an extension of the classical tensor contraction. The proposed tensor contraction introduces a nonlinear interaction operator that projects tensor factors onto the same intrinsic dimension for interaction, which not only allows nonlinear interactions but also frees them from the dimensional compatibility constraint. Equipped with the suggested tensor contraction, we revisit tensor network decompositions (such as tensor ring and fully connected tensor decompositions), allowing us to flexibly discover new and potential tensor network decompositions. To demonstrate the potential of the proposed new decompositions, we develop corresponding low-rank tensor completion models based on them. Moreover, we establish generalization error bounds between the tensor recovered by our model and the underlying tensor, providing a solid theoretical foundation for their superiority compared with classical tensor decomposition models. Extensive experiments on both synthetic and real-world data further demonstrate the numerical superiority of our method over state-of-the-art baselines.

Förderung

  • National Key R&D Program of China
  • Sichuan Science and Technology Program
  • National Natural Science Foundation of China

Zitieren

APA

Liu, S., Zhao, X., Jiang, Q., & Ng, M. K. (2026). Empowering Tensor Network Decompositions by Nonlinear and Incompatible Tensor Contraction. SIAM Journal on Imaging Sciences, 19(4), 2479-2511. https://doi.org/10.1137/25m182669x

Vancouver

Liu S, Zhao X, Jiang Q, Ng MK. Empowering Tensor Network Decompositions by Nonlinear and Incompatible Tensor Contraction. SIAM Journal on Imaging Sciences. 2026;19(4):2479-2511. doi:10.1137/25m182669x

BibTeX
@article{Liu2026,
  author = {Liu, Sheng and Zhao, Xi-Le and Jiang, Qin and Ng, Michael K.},
  title = {Empowering Tensor Network Decompositions by Nonlinear and Incompatible Tensor Contraction},
  journal = {SIAM Journal on Imaging Sciences},
  year = {2026},
  volume = {19},
  number = {4},
  pages = {2479--2511},
  doi = {10.1137/25m182669x}
}
Kostenlos starten →