Multi-Matrix Completion: A Novel Framework for Structurally Missing Elements
- 1 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (2) , 1626-1640
Abstract
A common assumption in matrix completion (MC) and tensor completion (TC) is that the missing locations are sampled randomly. However, in real-world scenarios, the unobserved elements are often not arbitrarily located, and may concentrate within entire rows or columns. We refer to this missing mechanism as structural missingness, and traditional MC and TC schemes suffer from drastic degradation under these circumstances. This work addresses the challenge of restoring structural missingness by introducing a novel framework for simultaneously reconstructing multiple matrices, called multi-matrix completion (MMC). In MMC, tri-factorization across matrices captures the correlation between matrices, and Tikhonov regularization on each matrix exploits its correlation. This design enables MMC to efficiently handle both random and structural missingness. In addition, MMC is not affected by the smoothness along matrices which makes it suitable for a wider variety of data compared to Fourier transform based TC methods. The alternating direction method of multipliers is utilized to solve the resultant optimization problem. The global convergence of the algorithm is supported by comprehensive theoretical analyses. We demonstrate the versatility of MMC through extensive experiments in image and video restoration, and showcase its superior performance in comparison to traditional MC and TC methods.Keywords
Funding Information
- Research Grants Council of the Hong Kong Special Administrative Region, China (CityU11207922)
This publication has 57 references indexed in Scilit:
- Tensor-based unsupervised feature selection for error-robust handling of unbalanced incomplete multi-view dataInformation Fusion, 2024
- Matrix Completion Methods for Causal Panel Data ModelsJournal of the American Statistical Association, 2021
- Joint Schatten $p$ p -norm and $\ell _p$ ℓ p -norm robust matrix completion for missing value recoveryKnowledge and Information Systems, 2013
- Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithmMathematical Programming Computation, 2012
- Factorization strategies for third-order tensorsLinear Algebra and its Applications, 2011
- Fixed point and Bregman iterative methods for matrix rank minimizationMathematical Programming, 2009
- Collaborative filtering using orthogonal nonnegative matrix tri-factorizationInformation Processing & Management, 2009
- CUR matrix decompositions for improved data analysisProceedings of the National Academy of Sciences, 2009
- Analysis of Individual Differences in Multidimensional Scaling Via an N-way Generalization of “Eckart-Young” DecompositionPsychometrika, 1970
- Some Mathematical Notes on Three-Mode Factor AnalysisPsychometrika, 1966