arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1707.05926cs.LG
收藏

LINE与矩阵分解的等价性

Equivalence between LINE and Matrix Factorization

School of Software, Tsinghua University(清华大学软件学院)

Qiao Wang, Zheng Wang, Xiaojun Ye

摘要:

LINE [1]作为一种有效的网络嵌入方法,在处理大规模无向、有向和/或加权网络时表现出了其有效性。特别地,它建议保留网络的局部结构(由一阶近似表示)和全局结构(由二阶近似表示)。在这项研究中,我们证明了具有这两个近似的LINE(LINE(1st)和LINE(2nd))实际上是分别分解两个不同的矩阵。具体来说,LINE(1st)是对矩阵M(1)进行因子分解,矩阵M(1)的条目是无向网络中顶点对的双倍逐点互信息(PMI),移位一个常数。LINE(2nd)是一个矩阵M(2)的分解,其元素是有向网络中顶点和上下文对的PMI,移动一个常数。我们希望这一发现将为LINE的进一步扩展和推广提供基础。

英文摘要:

LINE [1], as an efficient network embedding method, has shown its effectiveness in dealing with large-scale undirected, directed, and/or weighted networks. Particularly, it proposes to preserve both the local structure (represented by First-order Proximity) and global structure (represented by Second-order Proximity) of the network. In this study, we prove that LINE with these two proximities (LINE(1st) and LINE(2nd)) are actually factoring two different matrices separately. Specifically, LINE(1st) is factoring a matrix M (1), whose entries are the doubled Pointwise Mutual Information (PMI) of vertex pairs in undirected networks, shifted by a constant. LINE(2nd) is factoring a matrix M (2), whose entries are the PMI of vertex and context pairs in directed networks, shifted by a constant. We hope this finding would provide a basis for further extensions and generalizations of LINE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑