Dynamic guided metric representation learning for multi-view clustering

PeerJ Computer Science

Yuhang Wang¹  Tingyi Zheng²  Yilin Zhang³ 

[1] College of Data Science, Taiyuan University of Technology, Taiyuan, Shanxi, China;College of Information and Computer, Taiyuan University of Technology, Taiyuan, Shanxi, China;Software College, Taiyuan University of Technology, Taiyuan, Shanxi, China;

关键词: Multi-view clustering;    Dynamic routing;    Guided metric representation learning;    Fisher discriminant analysis;    Hilbert-Schmidt independence criteria;    Generalized canonical correlation analysis;   

DOI  :  10.7717/peerj-cs.922

来源: DOAJ

【 摘 要 】

Multi-view clustering (MVC) is a mainstream task that aims to divide objects into meaningful groups from different perspectives. The quality of data representation is the key issue in MVC. A comprehensive meaningful data representation should be with the discriminant characteristics in a single view and the correlation of multiple views. Considering this, a novel framework called Dynamic Guided Metric Representation Learning for Multi-View Clustering (DGMRL-MVC) is proposed in this paper, which can cluster multi-view data in a learned latent discriminated embedding space. Specifically, in the framework, the data representation can be enhanced by multi-steps. Firstly, the class separability is enforced with Fisher Discriminant Analysis (FDA) within each single view, while the consistence among different views is enhanced based on Hilbert-Schmidt independence criteria (HSIC). Then, the 1st enhanced representation is obtained. In the second step, a dynamic routing mechanism is introduced, in which the location or direction information is added to fulfil the expression. After that, a generalized canonical correlation analysis (GCCA) model is used to get the final ultimate common discriminated representation. The learned fusion representation can substantially improve multi-view clustering performance. Experiments validated the effectiveness of the proposed method for clustering tasks.

【 授权许可】

Unknown