.png){kind=icon}
返回
Salient and consensus representation learning based incomplete multiview clustering
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-022-03530-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multiview learning has a great potential to achieve a better performance than the conventional single-view based methods. However, some views of multiview data may be missing in the real-world applications. To cluster such incomplete multiview data, researchers tend to fill in the absent instances with the average vector of the available data for each view or adopt the pre-defined graphs from different views to learn a consensus representation. These approaches neither achieve the real distribution of the data nor explore the salient structure for each view influenced by noise. To address these problems, we propose a salient and consensus representation learning based method for incomplete multiview clustering (SCR_IMC). Firstly, we adaptively learn the salient structures of the collected data from different views adopting the self-representation property of the data. Then, the salient structures from different views are translated into the complete sub-spaces by a set of pre-defined projection matrices. Finally, a salient and consensus representation reflecting the common structure across different views is learned for the final clustering task. Experimental results on several real-world databases illustrate that the proposed method achieves competitive performance in comparison with the other classical and state-of-the-art methods, which proves the effectiveness of the proposed method.
Keyword:
Incomplete multiview clustering
Salient and consensus representation
Salient structure learning
Complete structure projection
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Multi-view manifold regularized learning-based method for prioritizing candidate disease miRNAs
PREAI
分享收藏CARM: Confidence-aware recommender model via review representation learning and historical rating behavior in the online platforms.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Joint Embedding Learning and Low-Rank Approximation: A Framework for Incomplete Multiview Learning
OAAI
OAAI分享收藏Global and Local-Contrast Guides Content-Aware Fusion for RGB-D Saliency Prediction用于rgb-d显着性预测的全局和局部对比度指南内容感知融合
PREAI
分享收藏
查看更多内容