Bayesian Nonparametric Poisson Factorization for Recommendation Systems

99 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Neural Autoregressive Approach to Collaborative Filtering (2016, positive): “Recently, Poisson Matrix Factorization (Gopalan et al., 2014b;a; 2013) was proposed, replacing Gaussian assumption of PMF by Poisson distribution.”
SHOPPER: A Probabilistic Model of Consumer Choice with Substitutes and Complements (2017, background): “, 2011; Wang and Blei, 2011; Gopalan, Hofman and Blei, 2015), potentially with an infinite number of latent parameters (Görür, Jäkel and Rasmussen, 2006; Gopalan et al., 2014).”
Scalable Recommendation with Hierarchical Poisson Factorization (2015, methodology): “Another recent work proposes a Bayesian non-parametric model [12] that adapts the dimensionality of the latent representations, learning the preference patterns (and their number) that best describe the users.”
General Latent Feature Models for Heterogeneous Datasets (2017, methodology): “In particular, these works assume that databases contain only either continuous data, usually modeled as Gaussian variables [12, 28], or discrete, that can be either modeled by discrete likelihoods [18, 24, 11] or simply treated as Gaussian variables [25, 2, 28].”