科研速览 · Science Skim继续刷下去 · Keep skimming →
◆ IEEE transactions on pattern analysis and machine intelligence2026-09-21

A Structure-Revealing Tensor Network Paradigm and Its Applications.

Yu-Bang Zheng, Xi-Le Zhao, Heng-Chao Li, Junhua Zeng, Chao Li, Qibin Zhao, Ting-Zhu Huang, Qing Zhu

原始摘要(英文原文)· Original abstract
Tensor network (TN) decomposition is a powerful data representation tool widely used in machine learning and computer vision. However, existing TN decomposition methods are limited by fixed topologies, which constrain their representational capacity. To overcome this limitation, we introduce, for the first time, an energy-based framework that allows us to reveal a data-adaptive TN structure through the optimization of an energy function. Specifically, we propose a novel structure-revealing TN paradigm, termed SVD-inspired TN decomposition (SVDinsTN). This paradigm enables the formulation of an energy function that simultaneously considers representation error and TN structure complexity, facilitating the joint optimization of data representation and the identification of a compact TN structure. Theoretically, we present the principles behind the energy function and derive an upper bound for the TN rank. In contrast to heuristic TN structure search methods, our energy-based method achieves a remarkable acceleration of 100 to 1000 times, making it practical for real-world applications. Experimental results in neural network compression, remote sensing image cloud removal, and tensor robust principal component analysis consistently show that SVDinsTN can identify a TN structure that better aligns with the given data, achieving superior performance over fixed-topology methods.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

A Structure-Revealing Tensor Network Paradigm and Its Applications. — 科研速览 Science Skim