Coupled Tensor Ring Completion
- 10 June 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Big Data
- Vol. PP (5) , 1-13
Abstract
Coupled tensor decomposition reveals the joint structure of multi-modal data by incorporating a priori knowledge from latent coupled factors. With the permutation-invariance property, tensor ring (TR) decomposition ensures the uniformity of decomposed factors and mode attributes, which can result in powerful representation capability in some multidimensional data processing applications. In this paper, we propose the low rank coupled TR model for completing missing entries of tensors with shared latent factors. The proposed model enables flexible coupling among an arbitrary number of tensors and can be efficiently solved via an alternating least squares algorithm. The excess risk bound for this model shows the theoretical performance enhancement in comparison with other coupled nuclear norm based methods. The analysis is validated on synthetic data, and experimental results on several real datasets demonstrate its superiority over the state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (W2412085)
- Innovation Research Foundation of National University of Defense Technology (202501-YJRC-XX-021)
This publication has 45 references indexed in Scilit:
- Mixed norm regularized models for low-rank tensor completionInformation Sciences, 2024
- Tensor Computation for Data Analysis2022
- Extraction of Common Task Features in EEG-fMRI Data Using Coupled Tensor-Tensor DecompositionBrain Topography, 2020
- Provable tensor ring completionSignal Processing, 2020
- Nesterov acceleration of alternating least squares for canonical tensor decomposition: Momentum step size selection and restart mechanismsNumerical Linear Algebra with Applications, 2020
- High-order tensor estimation via trains of coupled third-order CP and Tucker decompositionsLinear Algebra and its Applications, 2020
- Tensor rank learning in CP decomposition via convolutional neural networkSignal Processing: Image Communication, 2019
- Low rank tensor completion for multiway visual dataSignal Processing, 2019
- Link prediction in heterogeneous data via generalized coupled tensor factorizationData Mining and Knowledge Discovery, 2013
- Tensor factorization using auxiliary informationData Mining and Knowledge Discovery, 2012