Research Article
Multiview Subspace Clustering for Multi-kernel Low-Redundancy Representation Learning
@INPROCEEDINGS{10.1007/978-3-031-04245-4_25, author={Zhuo Wang and Ao Li and Jie Li and Yangwei Wang}, title={Multiview Subspace Clustering for Multi-kernel Low-Redundancy Representation Learning}, proceedings={6GN for Future Wireless Networks. 4th EAI International Conference, 6GN 2021, Huizhou, China, October 30--31, 2021, Proceedings}, proceedings_a={6GN}, year={2022}, month={5}, keywords={Multiview subspace clustering Multi-kernel Low-redundancy representation}, doi={10.1007/978-3-031-04245-4_25} }- Zhuo Wang
Ao Li
Jie Li
Yangwei Wang
Year: 2022
Multiview Subspace Clustering for Multi-kernel Low-Redundancy Representation Learning
6GN
Springer
DOI: 10.1007/978-3-031-04245-4_25
Abstract
The purpose of the multiview subspace clustering algorithm is to construct a consensus subspace representation matrix by looking for complementary information among multiple views. However, most of the existing algorithms only learn the common information shared between multiple views and ignore the different information among multiple views, which will also have a positive impact on the clustering effect. To solve this problem, we integrate the subspace representation matrix of all views, introduce tensor analysis, and learn to obtain the low-rank tensor subspace representation matrix to capture the high-order correlation between multiple views. Comprehensive experiments have been conducted on three data sets, and the experimental results show that the proposed algorithm is much better than the comparison algorithms in recent literature, and the superiority of the proposed algorithm is verified.
