Bayesian multi-tensor factorization

TL;DR

This paper presents Bayesian multi-tensor factorization, a novel probabilistic model that jointly factorizes multiple matrices and tensors, enabling flexible multi-view learning and relaxing traditional tensor assumptions.

Contribution

It introduces the first Bayesian framework for joint factorization of multiple matrices and tensors, allowing shared and private factors across diverse data structures.

Findings

Outperforms existing methods in toxicogenomics tasks

Effective in neuroimaging data analysis

Flexible modeling of multi-view data

Abstract

We introduce Bayesian multi-tensor factorization, a model that is the first Bayesian formulation for joint factorization of multiple matrices and tensors. The research problem generalizes the joint matrix-tensor factorization problem to arbitrary sets of tensors of any depth, including matrices, can be interpreted as unsupervised multi-view learning from multiple data tensors, and can be generalized to relax the usual trilinear tensor factorization assumptions. The result is a factorization of the set of tensors into factors shared by any subsets of the tensors, and factors private to individual tensors. We demonstrate the performance against existing baselines in multiple tensor factorization tasks in structural toxicogenomics and functional neuroimaging.