Multi-view hypergraph learning by patch alignment framework
Multi-view hypergraph learning by patch alignment framework
复制标题
DOI：
10.1016/j.neucom.2013.02.017
复制
发表时间：
2013-10
期刊：
影响因子：
6
通讯作者：
Chao-qun Hong;Jun Yu;Jonathan Li;Xuhui Chen
中科院分区：
文献类型：
--
作者：
Chao-qun Hong;Jun Yu;Jonathan Li;Xuhui Chen
基于图的降维方法是目前流行的降维方法。然而，它们大多存在数据间两两关系假设过于简单化的问题。特别是对于多视图数据，不同视图的不同关系很难集成到单个图中。本文提出了一种新的多视图数据的半监督降维方法。首先，我们将超图中的超边假设为补丁，并将超图应用于补丁对齐框架。其次，通过统计相邻对之间的距离来计算超边缘的权重，并对来自不同视图的补丁进行积分；通过构造多视图超图拉普拉斯矩阵，通过求解标准特征分解得到投影矩阵，得到降维数据。实验结果证明了该方法在检索性能上的有效性。
Graph-based methods are currently popular for dimensionality reduction. However, most of them suffer from over-simplified assumption of pairwise relationships among data. Especially for multi-view data, different relationships from different views are hard to be integrated into a single graph. In this paper, we propose a novel semi-supervised dimensionality reduction method for multi-view data. First, we assume the hyperedges in hypergraph as patches and apply hypergraph to the patch alignment framework. Second, the weights of the hyperedges are computed with statistics of distances between neighboring pairs and the patches from different views are integrated. In this way, we construct Multi-view Hypergraph Laplacian matrix and we get the dimensionality-reduced data by solving the standard eigen-decomposition to obtain the projection matrix. The experimental results demonstrate the effectiveness of the proposed method on retrieval performance.