Hierarchical Dirichlet Scaling Process

Dongwoo Kim, Alice Oh
Proceedings of the 31st International Conference on Machine Learning, PMLR 32(2):973-981, 2014.

Abstract

We present the hierarchical Dirichlet scaling process (HDSP), a Bayesian nonparametric mixed membership model for multi-labeled data. We construct the HDSP based on the gamma representation of the hierarchical Dirichlet process (HDP) which allows scaling the mixture components. With such construction, HDSP allocates a latent location to each label and mixture component in a space, and uses the distance between them to guide membership probabilities. We develop a variational Bayes algorithm for the approximate posterior inference of the HDSP. Through experiments on synthetic datasets as well as datasets of newswire, medical journal articles, and Wikipedia, we show that the HDSP results in better predictive performance than HDP, labeled LDA and partially labeled LDA.

Cite this Paper

BibTeX
@InProceedings{pmlr-v32-kim14, title = {Hierarchical Dirichlet Scaling Process}, author = {Kim, Dongwoo and Oh, Alice}, booktitle = {Proceedings of the 31st International Conference on Machine Learning}, pages = {973--981}, year = {2014}, editor = {Xing, Eric P. and Jebara, Tony}, volume = {32}, number = {2}, series = {Proceedings of Machine Learning Research}, address = {Bejing, China}, month = {22--24 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v32/kim14.pdf}, url = {https://proceedings.mlr.press/v32/kim14.html}, abstract = {We present the hierarchical Dirichlet scaling process (HDSP), a Bayesian nonparametric mixed membership model for multi-labeled data. We construct the HDSP based on the gamma representation of the hierarchical Dirichlet process (HDP) which allows scaling the mixture components. With such construction, HDSP allocates a latent location to each label and mixture component in a space, and uses the distance between them to guide membership probabilities. We develop a variational Bayes algorithm for the approximate posterior inference of the HDSP. Through experiments on synthetic datasets as well as datasets of newswire, medical journal articles, and Wikipedia, we show that the HDSP results in better predictive performance than HDP, labeled LDA and partially labeled LDA.} }
Endnote
%0 Conference Paper %T Hierarchical Dirichlet Scaling Process %A Dongwoo Kim %A Alice Oh %B Proceedings of the 31st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2014 %E Eric P. Xing %E Tony Jebara %F pmlr-v32-kim14 %I PMLR %P 973--981 %U https://proceedings.mlr.press/v32/kim14.html %V 32 %N 2 %X We present the hierarchical Dirichlet scaling process (HDSP), a Bayesian nonparametric mixed membership model for multi-labeled data. We construct the HDSP based on the gamma representation of the hierarchical Dirichlet process (HDP) which allows scaling the mixture components. With such construction, HDSP allocates a latent location to each label and mixture component in a space, and uses the distance between them to guide membership probabilities. We develop a variational Bayes algorithm for the approximate posterior inference of the HDSP. Through experiments on synthetic datasets as well as datasets of newswire, medical journal articles, and Wikipedia, we show that the HDSP results in better predictive performance than HDP, labeled LDA and partially labeled LDA.
RIS
TY - CPAPER TI - Hierarchical Dirichlet Scaling Process AU - Dongwoo Kim AU - Alice Oh BT - Proceedings of the 31st International Conference on Machine Learning DA - 2014/06/18 ED - Eric P. Xing ED - Tony Jebara ID - pmlr-v32-kim14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 32 IS - 2 SP - 973 EP - 981 L1 - http://proceedings.mlr.press/v32/kim14.pdf UR - https://proceedings.mlr.press/v32/kim14.html AB - We present the hierarchical Dirichlet scaling process (HDSP), a Bayesian nonparametric mixed membership model for multi-labeled data. We construct the HDSP based on the gamma representation of the hierarchical Dirichlet process (HDP) which allows scaling the mixture components. With such construction, HDSP allocates a latent location to each label and mixture component in a space, and uses the distance between them to guide membership probabilities. We develop a variational Bayes algorithm for the approximate posterior inference of the HDSP. Through experiments on synthetic datasets as well as datasets of newswire, medical journal articles, and Wikipedia, we show that the HDSP results in better predictive performance than HDP, labeled LDA and partially labeled LDA. ER -
APA
Kim, D. & Oh, A.. (2014). Hierarchical Dirichlet Scaling Process. Proceedings of the 31st International Conference on Machine Learning, in Proceedings of Machine Learning Research 32(2):973-981 Available from https://proceedings.mlr.press/v32/kim14.html.

Related Material