A hierarchical model for ordinal matrix factorization

42 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.

Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks (2015, methodology): “Instead, when α i < − 30 , we use the as recommended by Paquet et al. (2012).”
One-class collaborative filtering with random graphs (2013, background): “Obtaining a posterior approximation to (5) would follow known literature [20, 25], were it not for the unknown occurrence of edges hmn in H.”
Cold-start Active Learning with Robust Ordinal Matrix Factorization (2014, methodology): “…for CF for several reasons: i) they exhibit strong predictive performance, ii) they can deal formally with missing data and iii) they provide uncertainty estimates for predictions and parameter values (Salakhut-dinov & Mnih, 2008; Stern et al., 2009; Paquet et al., 2012; Marlin & Zemel, 2009).”
Probabilistic Matrix Factorization with Non-random Missing Data (2014, methodology): “We also ﬁnd that MF-MNAR outperforms the MAR version of this method, other state-of-the-art MF MAR alternatives (Paquet et al., 2012) as well as an alternative model for MNAR rating data based on mixtures of multinomials (Marlin & Zemel, 2009).”