fMKL-DR: A Fast Multiple Kernel Learning Framework with Dimensionality Reduction

2018 ◽  
pp. 153-165
Author(s):  
Thanh Trung Giang ◽  
Thanh Phuong Nguyen ◽  
Tran Quoc Vinh Nguyen ◽  
Dang Hung Tran
Keyword(s):  
Dimensionality Reduction ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Learning Framework ◽  
Multiple Kernel

scholarly journals A Novel Multiple Kernel Learning Framework for Heterogeneous Feature Fusion and Variable Selection

2012 ◽  
Vol 14 (3) ◽  
pp. 563-574 ◽  
Author(s):  
Yi-Ren Yeh ◽  
Ting-Chu Lin ◽  
Yung-Yu Chung ◽  
Yu-Chiang Frank Wang
Keyword(s):  
Variable Selection ◽  
Feature Fusion ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Learning Framework ◽  
Multiple Kernel ◽  
Heterogeneous Feature

Multiple Kernel Learning for Spectral Dimensionality Reduction

2015 ◽  
pp. 626-634 ◽  
Author(s):  
Diego Hernán Peluffo-Ordóñez ◽  
Andrés Eduardo Castro-Ospina ◽  
Juan Carlos Alvarado-Pérez ◽  
Edgardo Javier Revelo-Fuelagán
Keyword(s):  
Dimensionality Reduction ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Multiple Kernel ◽  
Spectral Dimensionality

scholarly journals Multiple Kernel Learning for Dimensionality Reduction

2011 ◽  
Vol 33 (6) ◽  
pp. 1147-1160 ◽  
Author(s):  
Yen-Yu Lin ◽  
Tyng-Luh Liu ◽  
Chiou-Shann Fuh
Keyword(s):  
Dimensionality Reduction ◽  
Multiple Kernel Learning ◽  
Kernel Learning ◽  
Multiple Kernel

A Conditional Entropy Minimization Criterion for Dimensionality Reduction and Multiple Kernel Learning

2010 ◽  
Vol 22 (11) ◽  
pp. 2887-2923 ◽  
Author(s):  
Hideitsu Hino ◽  
Noboru Murata
Keyword(s):  
Discriminant Analysis ◽  
Dimensionality Reduction ◽  
Multiple Kernel Learning ◽  
Conditional Entropy ◽  
Kernel Learning ◽  
Fisher Discriminant Analysis ◽  
Essential Information ◽  
Entropy Minimization ◽  
Fisher Discriminant ◽  
Multiple Kernel

Reducing the dimensionality of high-dimensional data without losing its essential information is an important task in information processing. When class labels of training data are available, Fisher discriminant analysis (FDA) has been widely used. However, the optimality of FDA is guaranteed only in a very restricted ideal circumstance, and it is often observed that FDA does not provide a good classification surface for many real problems. This letter treats the problem of supervised dimensionality reduction from the viewpoint of information theory and proposes a framework of dimensionality reduction based on class-conditional entropy minimization. The proposed linear dimensionality-reduction technique is validated both theoretically and experimentally. Then, through kernel Fisher discriminant analysis (KFDA), the multiple kernel learning problem is treated in the proposed framework, and a novel algorithm, which iteratively optimizes the parameters of the classification function and kernel combination coefficients, is proposed. The algorithm is experimentally shown to be comparable to or outperforms KFDA for large-scale benchmark data sets, and comparable to other multiple kernel learning techniques on the yeast protein function annotation task.

Sign in / Sign up

Export Citation Format

Share Document