首页> 外文期刊>Information Processing & Management >Orthogonal nonnegative matrix tri-factorization for co-clustering: Multiplicative updates on Stiefel manifolds
【24h】

Orthogonal nonnegative matrix tri-factorization for co-clustering: Multiplicative updates on Stiefel manifolds

机译:共聚的正交非负矩阵三因子分解:Stiefel流形上的乘法更新

获取原文
获取原文并翻译 | 示例
       

摘要

Matrix factorization-based methods become popular in dyadic data analysis, where a fundamental problem, for example, is to perform document clustering or co-clustering words and documents given a term-document matrix. Nonnegative matrix tri-factorization (NMTF) emerges as a promising tool for co-clustering, seeking a 3-factor decomposition X ≈ USV~T with all factor matrices restricted to be nonnegative, i.e., U ≥ 0,S ≥ 0, V ≥ 0. In this paper we develop multiplicative updates for orthogonal NMTF where X ≈ USV~T is pursued with orthogonality constraints, U~TU = I, and V~TV = I, exploiting true gradients on Stiefel manifolds. Experiments on various document data sets demonstrate that our method works well for document clustering and is useful in revealing polysemous words via co-clustering words and documents.
机译:基于矩阵分解的方法在二元数据分析中变得很普遍,其中一个基本问题是,例如,在给定术语文档矩阵的情况下执行文档聚类或共同聚类单词和文档。非负矩阵三因子分解(NMTF)成为一种有前途的共聚工具,它寻求三因子分解X≈USV〜T,且所有因子矩阵都限制为非负,即U≥0,S≥0,V≥ 0.在本文中,我们开发了正交NMTF的乘法更新,其中利用正交约束,U〜TU = I和V〜TV = I追求X≈USV〜T,并利用了Stiefel流形上的真实梯度。在各种文档数据集上进行的实验表明,我们的方法适用于文档聚类,并且可通过共同聚类单词和文档来揭示多义单词。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号