Factorized Topic Models
Machine Learning
2013-04-24 v7 Computer Vision and Pattern Recognition
Information Retrieval
Abstract
In this paper we present a modification to a latent topic model, which makes the model exploit supervision to produce a factorized representation of the observed data. The structured parameterization separately encodes variance that is shared between classes from variance that is private to each class by the introduction of a new prior over the topic space. The approach allows for a more eff{}icient inference and provides an intuitive interpretation of the data in terms of an informative signal together with structured noise. The factorized representation is shown to enhance inference performance for image, text, and video classification.
Cite
@article{arxiv.1301.3461,
title = {Factorized Topic Models},
author = {Cheng Zhang and Carl Henrik Ek and Andreas Damianou and Hedvig Kjellstrom},
journal= {arXiv preprint arXiv:1301.3461},
year = {2013}
}
Comments
ICLR 2013