Posterior Regularization on Bayesian Hierarchical Mixture Clustering
Machine Learning
2023-05-08 v7 Artificial Intelligence
Machine Learning
Abstract
Bayesian hierarchical mixture clustering (BHMC) improves traditionalBayesian hierarchical clustering by replacing conventional Gaussian-to-Gaussian kernels with a Hierarchical Dirichlet Process Mixture Model(HDPMM) for parent-to-child diffusion in the generative process. However,BHMC may produce trees with high nodal variance, indicating weak separation between nodes at higher levels. To address this issue, we employ Posterior Regularization, which imposes max-margin constraints on nodes at every level to enhance cluster separation. We illustrate how to apply PR toBHMC and demonstrate its effectiveness in improving the BHMC model.
Cite
@article{arxiv.2105.06903,
title = {Posterior Regularization on Bayesian Hierarchical Mixture Clustering},
author = {Weipeng Huang and Tin Lok James Ng and Nishma Laitonjam and Neil J. Hurley},
journal= {arXiv preprint arXiv:2105.06903},
year = {2023}
}