.png){kind=icon}
返回
Multiple Graph Regularized Concept Factorization With Adaptive Weights
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2876880.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Many traditional concept factorization methods employ single graph to approximate the manifold structure of data. Therefore, they cannot capture the underlying geometric structure hidden in data effectively. In this paper, we propose a novel method, called Multiple graph regularized Concept Factorization with Adaptive Weights (MCFAWs), for data representation. It exploits the intrinsic geometric manifold of the data by the linear combination of multiple graphs with parameter free. Therefore, our proposed MCFAW method can be applied to many real problems. Besides, an efficient optimization algorithm is presented to solve the proposed model. Some experimental results on the benchmarks show that the proposed MCFAW method outperforms the state-of-the-art methods.
Keyword:
Concept factorization
manifold
graph
parameter free
data representation
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
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏
查看更多内容