Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance

Abstract: 

Principal component analysis (PCA) and linear discriminant analysis (LDA) are the most well-known methods to reduce the dimensionality of feature vectors. However, both methods face challenges when used on multilabel data—each data point may be associated to multiple labels. PCA does not take advantage of label information thus the performance is sacrificed. LDA can exploit class information for multiclass data, but cannot be directly applied to multilabel problems. In this paper, we propose a novel dimensionality reduction method for multilabel data. We first introduce the generalized Hamming distance that measures the distance of two data points in the label space. Then the proposed distance is used in the graph embedding framework for feature dimension reduction. We verified the proposed method using three multilabel benchmark datasets and one large image dataset. The results show that the proposed feature dimensionality reduction method consistently outperforms PCA and other competing methods.

up
0 users have voted:

Paper Details

Authors:
Honglei Zhang, Moncef Gabbouj
Submitted On:
7 October 2018 - 1:32am
Short Link:
Type:
Poster
Event:
Presenter's Name:
Honglei Zhang
Paper Code:
3249
Document Year:
2018
Cite

Document Files

poster_ICIP_2018.pdf

(45)

Subscribe

[1] Honglei Zhang, Moncef Gabbouj, "Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance", IEEE SigPort, 2018. [Online]. Available: http://sigport.org/3582. Accessed: Apr. 20, 2019.
@article{3582-18,
url = {http://sigport.org/3582},
author = {Honglei Zhang; Moncef Gabbouj },
publisher = {IEEE SigPort},
title = {Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance},
year = {2018} }
TY - EJOUR
T1 - Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance
AU - Honglei Zhang; Moncef Gabbouj
PY - 2018
PB - IEEE SigPort
UR - http://sigport.org/3582
ER -
Honglei Zhang, Moncef Gabbouj. (2018). Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance. IEEE SigPort. http://sigport.org/3582
Honglei Zhang, Moncef Gabbouj, 2018. Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance. Available at: http://sigport.org/3582.
Honglei Zhang, Moncef Gabbouj. (2018). "Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance." Web.
1. Honglei Zhang, Moncef Gabbouj. Feature Dimensionality Reduction with Graph Embedding and Generalized Hamming Distance [Internet]. IEEE SigPort; 2018. Available from : http://sigport.org/3582