Exploiting the categorical reliability difference for binary classification

In binary pattern classification, the reliabilities of statistics obtained from the samples of the two categories are generally different. When the statistics are used for modeling a classifier, such reliability difference could impact the generalization performance. We formulate a disparity index t...

Full description

Saved in:
Bibliographic Details
Main Authors: Sun, Lei, Toh, Kar-Ann, Chen, Badong, Lin, Zhiping
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/145211
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-145211
record_format dspace
spelling sg-ntu-dr.10356-1452112020-12-15T04:48:08Z Exploiting the categorical reliability difference for binary classification Sun, Lei Toh, Kar-Ann Chen, Badong Lin, Zhiping School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Binary Classification Classification Algorithm In binary pattern classification, the reliabilities of statistics obtained from the samples of the two categories are generally different. When the statistics are used for modeling a classifier, such reliability difference could impact the generalization performance. We formulate a disparity index to show the statistical disparity based on the generalized eigenvalue decomposition of the categorical moment matrices. It is shown that this disparity index can effectively indicate the reliability difference between the two categories. The obtained reliability difference is subsequently utilized to adjust the regularization term of a classifier for effective learning generalization. Our experiments based on 10 real-world benchmark data sets validate the effectiveness of the proposed method. 2020-12-15T04:48:08Z 2020-12-15T04:48:08Z 2018 Journal Article Sun, L., Toh, K.-A., Chen, B., & Lin, Z. (2018). Exploiting the categorical reliability difference for binary classification. Journal of the Franklin Institute, 355(4), 2022-2040. doi:10.1016/j.jfranklin.2017.11.024 0016-0032 https://hdl.handle.net/10356/145211 10.1016/j.jfranklin.2017.11.024 4 355 2022 2040 en Journal of the Franklin Institute © 2017 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
Binary Classification
Classification Algorithm
spellingShingle Engineering::Electrical and electronic engineering
Binary Classification
Classification Algorithm
Sun, Lei
Toh, Kar-Ann
Chen, Badong
Lin, Zhiping
Exploiting the categorical reliability difference for binary classification
description In binary pattern classification, the reliabilities of statistics obtained from the samples of the two categories are generally different. When the statistics are used for modeling a classifier, such reliability difference could impact the generalization performance. We formulate a disparity index to show the statistical disparity based on the generalized eigenvalue decomposition of the categorical moment matrices. It is shown that this disparity index can effectively indicate the reliability difference between the two categories. The obtained reliability difference is subsequently utilized to adjust the regularization term of a classifier for effective learning generalization. Our experiments based on 10 real-world benchmark data sets validate the effectiveness of the proposed method.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Sun, Lei
Toh, Kar-Ann
Chen, Badong
Lin, Zhiping
format Article
author Sun, Lei
Toh, Kar-Ann
Chen, Badong
Lin, Zhiping
author_sort Sun, Lei
title Exploiting the categorical reliability difference for binary classification
title_short Exploiting the categorical reliability difference for binary classification
title_full Exploiting the categorical reliability difference for binary classification
title_fullStr Exploiting the categorical reliability difference for binary classification
title_full_unstemmed Exploiting the categorical reliability difference for binary classification
title_sort exploiting the categorical reliability difference for binary classification
publishDate 2020
url https://hdl.handle.net/10356/145211
_version_ 1688665378372190208