Low-rank kernel learning for graph-based clustering

Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen kernel matrix. To address this issue, previous multiple kernel l...

Full description

Saved in:
Bibliographic Details
Published in:Knowledge-based systems 2019-01, Vol.163, p.510-517
Main Authors: Kang, Zhao, Wen, Liangjian, Chen, Wenyu, Xu, Zenglin
Format: Article
Language:English
Subjects:
Clustering
Graph construction
Graphs
Kernels
Learning
Low-rank kernel matrix
Machine learning
Multiple kernel learning
Noise
Noise sensitivity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Constructing the adjacency graph is fundamental to graph-based clustering. Graph learning in kernel space has shown impressive performance on a number of benchmark data sets. However, its performance is largely determined by the chosen kernel matrix. To address this issue, previous multiple kernel learning algorithm has been applied to learn an optimal kernel from a group of predefined kernels. This approach might be sensitive to noise and limits the representation ability of the consensus kernel. In contrast to existing methods, we propose to learn a low-rank kernel matrix which exploits the similarity nature of the kernel matrix and seeks an optimal kernel from the neighborhood of candidate kernels. By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other. Extensive experimental results validate the efficacy of the proposed method.
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2018.09.009