基于XGBoost算法的社交网络链路预测  

Link Prediction of Social Network Based on XGBoost Algorithm

作　　者：陈耀飞 王友国[1] 朱亮[2] CHEN Yao-fei;WANG You-guo;ZHU Liang(College of Science,Nanjing University of Posts and Telecommunications;College of Telecommunications&Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学理学院 [2]南京邮电大学通信与信息工程学院,江苏南京210023

出　　处：《软件导刊》2019年第11期132-135,139,共5页Software Guide

基　　金：通信与网络技术国家工程研究中心开放研究基金项目(GCZX001)

摘　　要：提升链路预测精度是复杂网路研究的基础问题之一。传统基于局部信息相似性、基于全局信息相似性与基于随机游走相似性的链路预测都是基于单个相似性指标进行预测的,而没有充分利用这些相似性指标的综合信息。将链路预测问题看作机器学习中的二分类问题,将有连接的样本标签记为1,无连接的样本标签记为0,将基于局部信息、基于全局信息与基于随机游走相似性等15个指标作为样本特征。综合考虑以上信息,使用XGBoost算法,选取AUC作为模型评价准则,在facebook真实数据集上进行实验。结果表明,该算法在测试集上的AUC高于基于单个相似性指标链路预测的AUC。How to enhance the accuracy of link prediction is one of the fundamental problems in the research of complex networks.Traditional link prediction based on the local information similarity,the global information similarity and the random walk similarity make prediction based on a single similarity indicator,it dosen’t make full use of the comprehensive information of these indicators.In this paper,we study link prediction problem as binary problem in machine learning,we denote the label of linked sample as one,otherwise zero,then choose 15 similarity indicators based on local information,global information and random walk similarity,considering these information comprehensively,and using AUC as model evaluation criterion,we make experiments on facebook datasets with XGBoost algorithm,the result shows that the AUC of this algorithm is higher than that the AUC of link prediction based on similarity.

关 键 词：链路预测 XGBoost 机器学习 社交网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]