Hierarchical Maximum-Margin Clustering
Machine Learning
2015-02-09 v1 Computer Vision and Pattern Recognition
Abstract
We present a hierarchical maximum-margin clustering method for unsupervised data analysis. Our method extends beyond flat maximum-margin clustering, and performs clustering recursively in a top-down manner. We propose an effective greedy splitting criteria for selecting which cluster to split next, and employ regularizers that enforce feature sharing/competition for capturing data semantics. Experimental results obtained on four standard datasets show that our method outperforms flat and hierarchical clustering baselines, while forming clean and semantically meaningful cluster hierarchies.
Cite
@article{arxiv.1502.01827,
title = {Hierarchical Maximum-Margin Clustering},
author = {Guang-Tong Zhou and Sung Ju Hwang and Mark Schmidt and Leonid Sigal and Greg Mori},
journal= {arXiv preprint arXiv:1502.01827},
year = {2015}
}