Variational Inference For Probabilistic Latent Tensor Factorization with KL Divergence

TL;DR

This paper introduces a variational Bayesian inference method for Probabilistic Latent Tensor Factorization, enhancing modeling capabilities and inference accuracy for multi-way data analysis.

Contribution

It develops a full Bayesian variational inference approach for PLTF, enabling flexible model order selection and improved link prediction.

Findings

Effective model order selection demonstrated

Enhanced link prediction accuracy shown

Flexible inference framework established

Abstract

Probabilistic Latent Tensor Factorization (PLTF) is a recently proposed probabilistic framework for modelling multi-way data. Not only the common tensor factorization models but also any arbitrary tensor factorization structure can be realized by the PLTF framework. This paper presents full Bayesian inference via variational Bayes that facilitates more powerful modelling and allows more sophisticated inference on the PLTF framework. We illustrate our approach on model order selection and link prediction.