Inferring Latent Structure From Mixed Real and Categorical Relational Data

Salazar, E

Cain, MS

Darling, EF

Mitroff, SR

Carin, L

2014-07-22T16:18:52Z

We consider analysis of relational data (a matrix), in which the rows correspond to subjects (e.g., people) and the columns correspond to attributes. The elements of the matrix may be a mix of real and categorical. Each subject and attribute is characterized by a latent binary feature vector, and an inferred matrix maps each row-column pair of binary feature vectors to an observed matrix element. The latent binary features of the rows are modeled via a multivariate Gaussian distribution with low-rank covariance matrix, and the Gaussian random variables are mapped to latent binary features via a probit link. The same type construction is applied jointly to the columns. The model infers latent, low-dimensional binary features associated with each row and each column, as well correlation structure between all rows and between all columns.

http://arxiv.org/abs/1206.6469v1

https://hdl.handle.net/10161/8953

icml.cc / Omnipress

cs.LG

cs.LG

stat.ML

Inferring Latent Structure From Mixed Real and Categorical Relational Data

Journal article

http://arxiv.org/abs/1206.6469v1

Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

Center for Cognitive Neuroscience

Duke

Duke Institute for Brain Sciences

Electrical and Computer Engineering

Faculty

Institutes and Provost's Academic Units

Pratt School of Engineering

Psychology and Neuroscience

Trinity College of Arts & Sciences

University Institutes and Centers