基于图谱理论几何空间结构变换的大数据核聚类算法

摘要

For the problem that the existing kernel clustering approaches need to learn the entire kernel matrix with the low compute efficiency,aimed at it proposed a clustering approach based on the spectral.Firstly,it based on spectral construct the similarity graph;then,computed the Laplacian matrix for the graph and select little part of the matrix to learn;lastly,realized the classification with kernel K-means approach.The simulating results prove that the proposed approach has better compute efficiency than the other kernel clustering approaches with a comparable clustering performance and works for big scale data.%现有核聚类算法需要学习完整的核矩阵，计算效率较低，仅适用于小规模数据，对此提出了基于图谱理论的核函数分类算法。首先，基于图谱理论建立无标记数据的相似度图；然后，计算其拉普拉斯矩阵，并选取拉普拉斯矩阵的部分特征向量来学习；最后，利用核 K-means 算法实现数据分类。对比实验结果证明，本算法在具有较好聚类性能的前提下，计算效率明显优于其他同类型算法，并适合中型及大型规模数据分类处理。