Cumulative Restricted Boltzmann Machines for Ordinal Matrix Data Analysis

Truyen Tran, Dinh Phung, Svetha Venkatesh
Proceedings of the Asian Conference on Machine Learning, PMLR 25:411-426, 2012.

Abstract

Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc. This paper investigates modelling of ordinal data with Gaussian restricted Boltzmann machines (RBMs). In particular, we present the model architecture, learning and inference procedures for both vector-variate and matrix-variate ordinal data. We show that our model is able to capture latent opinion profile of citizens around the world, and is competitive against state-of-art collaborative filtering techniques on large-scale public datasets. The model thus has the potential to extend application of RBMs to diverse domains such as recommendation systems, product reviews and expert assessments.

Cite this Paper

BibTeX
@InProceedings{pmlr-v25-tran12a, title = {Cumulative Restricted {B}oltzmann Machines for Ordinal Matrix Data Analysis}, author = {Tran, Truyen and Phung, Dinh and Venkatesh, Svetha}, booktitle = {Proceedings of the Asian Conference on Machine Learning}, pages = {411--426}, year = {2012}, editor = {Hoi, Steven C. H. and Buntine, Wray}, volume = {25}, series = {Proceedings of Machine Learning Research}, address = {Singapore Management University, Singapore}, month = {04--06 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v25/tran12a/tran12a.pdf}, url = {https://proceedings.mlr.press/v25/tran12a.html}, abstract = {Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc. This paper investigates modelling of ordinal data with Gaussian restricted Boltzmann machines (RBMs). In particular, we present the model architecture, learning and inference procedures for both vector-variate and matrix-variate ordinal data. We show that our model is able to capture latent opinion profile of citizens around the world, and is competitive against state-of-art collaborative filtering techniques on large-scale public datasets. The model thus has the potential to extend application of RBMs to diverse domains such as recommendation systems, product reviews and expert assessments.} }
Endnote
%0 Conference Paper %T Cumulative Restricted Boltzmann Machines for Ordinal Matrix Data Analysis %A Truyen Tran %A Dinh Phung %A Svetha Venkatesh %B Proceedings of the Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2012 %E Steven C. H. Hoi %E Wray Buntine %F pmlr-v25-tran12a %I PMLR %P 411--426 %U https://proceedings.mlr.press/v25/tran12a.html %V 25 %X Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc. This paper investigates modelling of ordinal data with Gaussian restricted Boltzmann machines (RBMs). In particular, we present the model architecture, learning and inference procedures for both vector-variate and matrix-variate ordinal data. We show that our model is able to capture latent opinion profile of citizens around the world, and is competitive against state-of-art collaborative filtering techniques on large-scale public datasets. The model thus has the potential to extend application of RBMs to diverse domains such as recommendation systems, product reviews and expert assessments.
RIS
TY - CPAPER TI - Cumulative Restricted Boltzmann Machines for Ordinal Matrix Data Analysis AU - Truyen Tran AU - Dinh Phung AU - Svetha Venkatesh BT - Proceedings of the Asian Conference on Machine Learning DA - 2012/11/17 ED - Steven C. H. Hoi ED - Wray Buntine ID - pmlr-v25-tran12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 25 SP - 411 EP - 426 L1 - http://proceedings.mlr.press/v25/tran12a/tran12a.pdf UR - https://proceedings.mlr.press/v25/tran12a.html AB - Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc. This paper investigates modelling of ordinal data with Gaussian restricted Boltzmann machines (RBMs). In particular, we present the model architecture, learning and inference procedures for both vector-variate and matrix-variate ordinal data. We show that our model is able to capture latent opinion profile of citizens around the world, and is competitive against state-of-art collaborative filtering techniques on large-scale public datasets. The model thus has the potential to extend application of RBMs to diverse domains such as recommendation systems, product reviews and expert assessments. ER -
APA
Tran, T., Phung, D. & Venkatesh, S.. (2012). Cumulative Restricted Boltzmann Machines for Ordinal Matrix Data Analysis. Proceedings of the Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 25:411-426 Available from https://proceedings.mlr.press/v25/tran12a.html.

Related Material