Deakin University
Browse

File(s) under permanent embargo

Dirichlet process mixture models with pairwise constraints for data clustering

Version 2 2024-06-06, 01:30
Version 1 2016-05-31, 17:00
journal contribution
posted on 2024-06-06, 01:30 authored by C Li, Santu RanaSantu Rana, Q Phung, Svetha VenkateshSvetha Venkatesh
The Dirichlet process mixture (DPM) model, a typical Bayesian nonparametric model, can infer the number of clusters automatically, and thus performing priority in data clustering. This paper investigates the influence of pairwise constraints in the DPM model. The pairwise constraint, known as two types: must-link (ML) and cannot-link (CL) constraints, indicates the relationship between two data points. We have proposed two relevant models which incorporate pairwise constraints: the constrained DPM (C-DPM) and the constrained DPM with selected constraints (SCDPM). In C-DPM, the concept of chunklet is introduced. ML constraints are compiled into chunklets and CL constraints exist between chunklets.We derive the Gibbs sampling of the C-DPM based on chunklets. We further propose a principled approach to select the most useful constraints, which will be incorporated into the SC-DPM. We evaluate the proposed models based on three real datasets: 20 Newsgroups dataset, NUS-WIDE image dataset and Facebook comments datasets we collected by ourselves. Our SC-DPM performs priority in data clustering. In addition, our SC-DPM can be potentially used for short-text clustering.

History

Journal

Annals of data science

Volume

3

Pagination

205-223

Location

Berlin, Germany

ISSN

2198-5804

eISSN

2198-5812

Language

eng

Publication classification

C Journal article, C1 Refereed article in a scholarly journal

Copyright notice

2016, Springer

Issue

2

Publisher

Springer