Personalized Coupled Tensor Decomposition for Multimodal Data Fusion: Uniqueness and Algorithms

Abstract

Coupled tensor decompositions (CTDs) perform data fusion by linking factors from different datasets. Although many CTDs have been already proposed, current works do not address important challenges of data fusion, where: 1) the datasets are often heterogeneous, constituting different "views" of a given phenomena (multimodality); and 2) each dataset can contain personalized or dataset-specific information, constituting distinct factors that are not coupled with other datasets. In this work, we introduce a personalized CTD framework tackling these challenges. A flexible model is proposed where each dataset is represented as the sum of two components, one related to a common tensor through a multilinear measurement model, and another specific to each dataset. Both the common and distinct components are assumed to admit a polyadic decomposition. This generalizes several existing CTD models. We provide conditions for specific and generic uniqueness of the decomposition that are easy to interpret. These conditions employ uni-mode uniqueness of different individual datasets and properties of the measurement model. Two algorithms are proposed to compute the common and distinct components: a semi-algebraic one and a coordinate-descent optimization method. Experimental results illustrate the advantage of the proposed framework compared with the state of the art approaches.

References in corpus (23)

• Spectral Variability in Hyperspectral Data Unmixing: A Comprehensive Review
• Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
• On the Uniqueness of the Canonical Polyadic Decomposition of third-order tensors --- Part II: Uniqueness of the overall decomposition
• Generalized Canonical Polyadic Tensor Decomposition
• Canonical polyadic decomposition of third-order tensors: reduction to generalized eigenvalue decomposition
• On the Uniqueness of the Canonical Polyadic Decomposition of third-order tensors --- Part I: Basic Results and Uniqueness of One Factor Matrix
• Spectrum Cartography via Coupled Block-Term Tensor Decomposition
• Tensor Analysis and Fusion of Multimodal Brain Images
• Hyperspectral Super-Resolution with Coupled Tucker Approximation: Recoverability and SVD-based algorithms
• Coupled Tensor Decomposition for Hyperspectral and Multispectral Image Fusion with Inter-Image Variability
• Exploring multimodal data fusion through joint decompositions with flexible couplings
• Tensor Completion from Regular Sub-Nyquist Samples
• Double Coupled Canonical Polyadic Decomposition for Joint Blind Source Separation
• Tensor-Based Fusion of EEG and FMRI to Understand Neurological Changes in Schizophrenia
• Computing Large-Scale Matrix and Tensor Decomposition with Structured Factors: A Unified Nonconvex Optimization Perspective
• A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings
• AFFIRM: Affinity Fusion-based Framework for Iteratively Random Motion correction of multi-slice fetal brain MRI
• Nonlinear Multiview Analysis: Identifiability and Neural Network-assisted Implementation
• Stochastic Mirror Descent for Low-Rank Tensor Decomposition Under Non-Euclidean Losses
• Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
• Personalized PCA: Decoupling Shared and Unique Features
• Coupled CP tensor decomposition with shared and distinct components for multi-task fMRI data fusion
• Heterogeneous Matrix Factorization: When Features Differ by Datasets