A Flexible Optimization Framework for Regularized Matrix-Tensor Factorizations with Linear Couplings

Abstract

Coupled matrix and tensor factorizations (CMTF) are frequently used to jointly analyze data from multiple sources, also called data fusion. However, different characteristics of datasets stemming from multiple sources pose many challenges in data fusion and require to employ various regularizations, constraints, loss functions and different types of coupling structures between datasets. In this paper, we propose a flexible algorithmic framework for coupled matrix and tensor factorizations which utilizes Alternating Optimization (AO) and the Alternating Direction Method of Multipliers (ADMM). The framework facilitates the use of a variety of constraints, loss functions and couplings with linear transformations in a seamless way. Numerical experiments on simulated and real datasets demonstrate that the proposed approach is accurate, and computationally efficient with comparable or better performance than available CMTF methods for Frobenius norm loss, while being more flexible. Using Kullback-Leibler divergence on count data, we demonstrate that the algorithm yields accurate results also for other loss functions.

References in corpus (16)

• A Variable Splitting Augmented Lagrangian Approach to Linear Spectral Unmixing
• Optimal parameter selection for the alternating direction method of multipliers (ADMM): quadratic problems
• On Tensors, Sparsity, and Nonnegative Factorizations
• All-at-once Optimization for Coupled Matrix and Tensor Factorizations
• Hyperspectral Super-Resolution: A Coupled Tensor Factorization Approach
• Accelerated Multiplicative Updates and Hierarchical ALS Algorithms for Nonnegative Matrix Factorization
• A Flexible and Efficient Algorithmic Framework for Constrained Matrix and Tensor Factorization
• Generalized Canonical Polyadic Tensor Decomposition
• Parallel Algorithms for Constrained Tensor Factorization via the Alternating Direction Method of Multipliers
• Hyperspectral Unmixing: Ground Truth Labeling, Datasets, Benchmark Performances and Survey
• Joint Tensor Factorization and Outlying Slab Suppression with Applications
• Exploring multimodal data fusion through joint decompositions with flexible couplings
• Flexible Multi-layer Sparse Approximations of Matrices and Applications
• Bayesian multi-tensor factorization
• Separating common (global and local) and distinct variation in multiple mixed types data sets
• COPA: Constrained PARAFAC2 for Sparse & Large Datasets

Cited by in corpus (7)

• An AO-ADMM approach to constraining PARAFAC2 on all modes
• Unsupervised EHR-based Phenotyping via Matrix and Tensor Decompositions
• Personalized Coupled Tensor Decomposition for Multimodal Data Fusion: Uniqueness and Algorithms
• PARAFAC2-based Coupled Matrix and Tensor Factorizations
• PARAFAC2 AO-ADMM: Constraints in all modes
• tPARAFAC2: Tracking evolving patterns in (incomplete) temporal data
• PARAFAC2-based Coupled Matrix and Tensor Factorizations with Constraints