基于全局融合的多核概念分解算法
2019-08-01李飞杜亮任超宏
李飞 杜亮 任超宏



摘 要:非负矩阵分解(NMF)算法仅能用于对原始非负数据寻找低秩近似,而概念分解(CF)算法将矩阵分解模型扩展到单个非线性核空间,提升了矩阵分解算法的学习能力和普适性。针对无监督环境下概念分解面临的如何设计或选择合适核函数这一问题,提出基于全局融合的多核概念分解(GMKCF)算法。同时输入多种候选核函数,在概念分解框架下基于全局线性权重融合对它们进行学习,以得出质量高稳定性好的聚类结果,并解决概念分解模型面臨核函数选择的问题。采用交替迭代的方法对新模型进行求解,证明了算法的收敛性。
将该算法与基于核的K-均值(KKM)、谱聚类(SC)、KCF(Kernel Concept Factorization)、Coreg(Co-regularized multi-view spectral clustering)、RMKKM(Robust Multiple KKM)在多个真实数据库上的实验结果表明,该算法在数据聚类方面优于对比算法。
关键词:多核学习;概念分解;矩阵分解;多核聚类;全局融合
中图分类号:TP181
文献标志码:A
文章编号:1001-9081(2019)04-1021-06
Abstract: Non-negative Matrix Factorization (NMF) algorithm can only be used to find low rank approximation of original non-negative data while Concept Factorization (CF) algorithm extends matrix factorization to single non-linear kernel space, improving learning ability and adaptability of matrix factorization. In unsupervised environment, to design or select proper kernel function for specific dataset, a new algorithm called Globalized Multiple Kernel CF (GMKCF) was proposed. Multiple candidate kernel functions were input in the same time and learned in the CF framework based on global linear fusion, obtaining a clustering result with high quality and stability and solving the problem of kernel function selection that the CF faced. The convergence of the proposed algorithm was verified by solving the model with alternate iteration. The experimental results on several real databases show that the proposed algorithm outperforms comparison algorithms in data clustering, such as Kernel K-Means (KKM), Spectral Clustering (SC), Kernel CF (KCF), Co-regularized multi-view spectral clustering (Coreg), and Robust Multiple KKM (RMKKM).
Key words: multiple kernel learning; Concept Factorization (CF); matrix factorization; multiple kernel clustering; global fusion
0 引言
数据挖掘从看似无序的数据中寻找有序、有价值的信息。聚类分析是数据挖掘、机器学习中的一项重要技术,也是国内外学者研究的一个重点领域。聚类技术可用来探索数据的内部结构,并就其某种相关关系进行挖掘,因而在很多领域中得到广泛应用,例如:在电子商务中,应用聚类算法可以发现不同客户群体,有利于寻找潜在市场;在生物学领域,可以对基因、蛋白质等进行聚类研究,从而获取对其结构的深入认识;在互联网上,可以对微博、新闻中的文档进行聚类研究,从而进行热点事件发现等。……
