Abstract
Using multi-kernel learning to deal with the non-linear relationship of data has become a new research topic in the field of multi-view subspace clustering. However, the existing methods have the following three defects: 1) the simple consensus kernel weighting strategy cannot give full play to the advantages of multiple kernels; 2) they are sensitive to non-Gaussian noise and their learning affinity matrices cannot meet the block diagonal properties required by clustering, resulting in low clustering performance; 3) the complementary feature information between the data of each view cannot be fully mined. In this paper, a novel robust multi-view subspace clustering method is proposed based on weighted multi-kernel learning and co-regularization (WMKMSC). Based on the self-expression learning framework, block diagonal regularizer (BDR), multi-kernel learning strategy and co-regularization are integrated into the proposed model. Especially, as a robust learning method, the mixture correntropy is used to construct a robust multi-kernel weighting strategy, which is helpful to learn the best consensus kernel. Our method is more effective and robust than several of the most advanced methods on five commonly used datasets.
Highlights
In view of the subspace embedding characteristics of high-dimensional data manifold, subspace clustering (SC), a new clustering idea and pattern, has been proposed, and soon becomes a research hot-spot of algorithms for high-dimensional data clustering [1]
At present, there is no multi-view subspace clustering algorithm that can achieve the following goals simultaneously: 1) the affinity matrix obtained by the self-expressing framework has a strong block diagonal attribute; 2) an effective kernel weighting strategy can be built to take full advantage of multiple kernels; 3) it can effectively process the nonlinear structure in the data and suppress the complex noise in the data; 4) it can effectively mine the complementary information between each view
This paper proposes a novel multi-view subspace clustering method (WMKMSC) that integrates BDR, ‘‘kernel trick’’, multiple kernel learning (MKL) and co-regularization
Summary
In view of the subspace embedding characteristics of high-dimensional data manifold, subspace clustering (SC), a new clustering idea and pattern, has been proposed, and soon becomes a research hot-spot of algorithms for high-dimensional data clustering [1]. At present, there is no multi-view subspace clustering algorithm that can achieve the following goals simultaneously: 1) the affinity matrix obtained by the self-expressing framework has a strong block diagonal attribute; 2) an effective kernel weighting strategy can be built to take full advantage of multiple kernels; 3) it can effectively process the nonlinear structure in the data and suppress the complex noise in the data; 4) it can effectively mine the complementary information between each view. These four goals play an important role in improving the clustering performance of multi-view data and the robustness of the model.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
