Publication details

Simultaneous Visualization of Samples, Features and Multi-Labels

Conference Paper (international conference)

Kudo M., Kimura K., Haindl Michal, Tenmoto H.

serial: Proceedings of the 23rd International Conference on Pattern Recognition (ICPR), p. 3592-3597

action: 23rd International Conference on Pattern Recognition ICPR 2016, (Cancún, MX, 20161204)

project(s): 15H02719, JSPS KAKENHI

keywords: Visualization, matrix factorization

preview: Download

abstract (eng):

Visualization helps us to understand single-label and multi-label classification problems. In this paper, we show several standard techniques for simultaneous visualization of samples, features and multi-classes on the basis of linear regression and matrix factorization. The experiment with two real-life multilabel datasets showed that such techniques are effective to know how labels are correlated to each other and how features are related to labels in a given multi-label classification problem.