Deep Dirichlet process mixture models

Naiqi Li, Wenjie Li, Yong Jiang, Shu-Tao Xia
Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, PMLR 180:1138-1147, 2022.

Abstract

In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning. The traditional Dirichlet process mixture model can infer the number of mixture components, but its flexibility is restricted since the clustering is performed in the raw feature space. Our method alleviates this limitation by using the flow-based deep neural network to learn more expressive features. DDPM unifies Dirichlet processes and the flow-based model with Monte Carlo expectation-maximization, and uses Gibbs sampling to sample from the posterior. This combination allows our method to exploit the mutually beneficial relation between clustering and feature learning. The effectiveness of DDPM is demonstrated by thorough experiments in various synthetic and real-world datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v180-li22c, title = {Deep Dirichlet process mixture models}, author = {Li, Naiqi and Li, Wenjie and Jiang, Yong and Xia, Shu-Tao}, booktitle = {Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence}, pages = {1138--1147}, year = {2022}, editor = {Cussens, James and Zhang, Kun}, volume = {180}, series = {Proceedings of Machine Learning Research}, month = {01--05 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v180/li22c/li22c.pdf}, url = {https://proceedings.mlr.press/v180/li22c.html}, abstract = {In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning. The traditional Dirichlet process mixture model can infer the number of mixture components, but its flexibility is restricted since the clustering is performed in the raw feature space. Our method alleviates this limitation by using the flow-based deep neural network to learn more expressive features. DDPM unifies Dirichlet processes and the flow-based model with Monte Carlo expectation-maximization, and uses Gibbs sampling to sample from the posterior. This combination allows our method to exploit the mutually beneficial relation between clustering and feature learning. The effectiveness of DDPM is demonstrated by thorough experiments in various synthetic and real-world datasets.} }
Endnote
%0 Conference Paper %T Deep Dirichlet process mixture models %A Naiqi Li %A Wenjie Li %A Yong Jiang %A Shu-Tao Xia %B Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2022 %E James Cussens %E Kun Zhang %F pmlr-v180-li22c %I PMLR %P 1138--1147 %U https://proceedings.mlr.press/v180/li22c.html %V 180 %X In this paper we propose the deep Dirichlet process mixture (DDPM) model, which is an unsupervised method that simultaneously performs clustering and feature learning. The traditional Dirichlet process mixture model can infer the number of mixture components, but its flexibility is restricted since the clustering is performed in the raw feature space. Our method alleviates this limitation by using the flow-based deep neural network to learn more expressive features. DDPM unifies Dirichlet processes and the flow-based model with Monte Carlo expectation-maximization, and uses Gibbs sampling to sample from the posterior. This combination allows our method to exploit the mutually beneficial relation between clustering and feature learning. The effectiveness of DDPM is demonstrated by thorough experiments in various synthetic and real-world datasets.
APA
Li, N., Li, W., Jiang, Y. & Xia, S.. (2022). Deep Dirichlet process mixture models. Proceedings of the Thirty-Eighth Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 180:1138-1147 Available from https://proceedings.mlr.press/v180/li22c.html.

Related Material