Discriminative Clustering via Generative Feature Mapping

Authors

  • Liwei Wang The Chinese University of Hong Kong
  • Xiong Li Shanghai Jiao Tong University
  • Zhuowen Tu Microsoft Research Asia and UCLA
  • Jiaya Jia The Chinese University of Hong Kong

Keywords:

feature mapping, discriminative clustering, generative and discriminative models

Abstract

Existing clustering methods can be roughly classified into two categories: generative and discriminative approaches. Generative clustering aims to explain the data and thus is adaptive to the underlying data distribution; discriminative clustering, on the other hand, emphasizes on finding partition boundaries. In this paper, we take the advantages of both models by coupling the two paradigms through feature mapping derived from linearizing Bayesian classifiers. Such the feature mapping strategy maps nonlinear boundaries of generative clustering to linear ones in the feature space where we explicitly impose the maximum entropy principle. We also propose the unified probabilistic framework, enabling solvers using standard techniques. Experiments on a variety of datasets bear out the notable benefit of our method in terms of adaptiveness and robustness.

Downloads

Published

2021-09-20

How to Cite

Wang, L., Li, X., Tu, Z., & Jia, J. (2021). Discriminative Clustering via Generative Feature Mapping. Proceedings of the AAAI Conference on Artificial Intelligence, 26(1), 1162-1168. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/8305

Issue

Section

AAAI Technical Track: Machine Learning