.png){kind=icon}
返回
Semi-supervised multi-view clustering based on constrained nonnegative matrix factorization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2019.06.006.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most existing clustering approaches address multi-view clustering problems by graph regularized nonnegative matrix factorization to obtain the new representation of each view separately. And then, the additional regularization term is introduced to fuse these representations. However, the graph regularization is no guarantee that the representation obtained by mapping data points has the consistent label information with the original data. In addition, we may have a number of labeled samples in practice. This paper proposes a new semi-supervised multi-view clustering method based on Constrained Nonnegative Matrix Factorization with sparseness constraint, which is called MVCNMF. Our method first learns the representation by introducing an auxiliary matrix for each view and constructs the label constraint matrix shared among all views, where the label constraint matrix can guarantee that the label information is fused into the new representation of each view. Then, by applying the co-regularization and the sparseness constraint in auxiliary matrices, the complementary information from different views is integrated, and the robust feature of each view is extracted. Further, we also present the convergence proof and the computational complexity analysis of our method. Finally, extensive experiments on real datasets have demonstrated that our proposed approach can achieve a better clustering quality as compared to state-of-the-art multi-view clustering methods. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Multi-view
Clustering
Constrained nonnegative matrix factorization
Sparseness constraint
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.2W
被引数:
4.5W
机构
引用论文
A study on the glass transition behavior and morphology of semi-interpenetrating polymer networks
PREAI
分享收藏Multi-view clustering via multi-manifold regularized non-negative matrix factorization.png)
NEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
查看更多内容