Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICDM.2011.147
Title: Towards optimal discriminating order for multiclass classification
Authors: Liu, D.
Yan, S. 
Mu, Y. 
Hua, X.-S.
Chang, S.-F.
Zhang, H.-J.
Keywords: Discriminating order
Multiclass
Sequential Discriminating Tree
Issue Date: 2011
Source: Liu, D.,Yan, S.,Mu, Y.,Hua, X.-S.,Chang, S.-F.,Zhang, H.-J. (2011). Towards optimal discriminating order for multiclass classification. Proceedings - IEEE International Conference on Data Mining, ICDM : 388-397. ScholarBank@NUS Repository. https://doi.org/10.1109/ICDM.2011.147
Abstract: In this paper, we investigate how to design an optimized discriminating order for boosting multiclass classification. The main idea is to optimize a binary tree architecture, referred to as Sequential Discriminating Tree (SDT), that performs the multiclass classification through a hierarchical sequence of coarse-to-fine binary classifiers. To infer such a tree architecture, we employ the constrained large margin clustering procedure which enforces samples belonging to the same class to locate at the same side of the hyperplane while maximizing the margin between these two partitioned class subsets. The proposed SDT algorithm has a theoretic error bound which is shown experimentally to effectively guarantee the generalization performance. Experiment results indicate that SDT clearly beats the state-of-the-art multiclass classification algorithms. © 2011 IEEE.
Source Title: Proceedings - IEEE International Conference on Data Mining, ICDM
URI: http://scholarbank.nus.edu.sg/handle/10635/72056
ISBN: 9780769544083
ISSN: 15504786
DOI: 10.1109/ICDM.2011.147
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

2
checked on Dec 13, 2017

Page view(s)

23
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.