基于监督联合去噪模型的社交网络链接预测  

Link prediction in online social networks based on supervised joint denoising model

作　　者：郝占刚[1] 章伟雄 陈政 

机构地区：[1]山东工商学院工商管理学院 [2]Department of Computer Science and Engineering, Washington University

出　　处：《中国科学：信息科学》2017年第11期1551-1565,共15页Scientia Sinica(Informationis)

基　　金：国家自然科学基金(批准号:71672103;61572104;71501113);山东省自然科学基金(批准号:ZR2017MG022)资助项目

摘　　要：社交网络链接预测能够获取丢失链接的重要信息,在很多领域都有应用.现有链接预测算法或因无法充分利用信息或因无法捕获全部特性而在链接预测精度上有所欠缺.为提高链接预测精度,本文提出一种新的算法——监督联合去噪模型(supervised joint denoising model,SJDM),该算法把链接预测问题看作一个有监督的矩阵"去噪"问题.为了能够获取理想社交网络矩阵,该算法综合利用现有用户特征信息和链接信息去训练一个映射函数.该函数能够通过现有社交网络链接矩阵获取理想社交网络链接矩阵,完成链接预测.获取的理想社交网络链接矩阵是一个权重矩阵,采用该矩阵进行社区发现能取得比采用原矩阵更佳的效果.本文采用5个真实社交网络对SJDM算法进行了验证,实验结果证明了该算法的有效性.Link prediction of social networks can capture important information about missing links for applications in many fields. Because of the failure to make full use of information as well as capture all properties,the link prediction precision of most of methods is low. For higher precision, we propose a novel algorithm, a supervised joint denoising model（SJDM） that formulates the link prediction problem as a supervised matrix＂denoising＂ problem. The central piece of our method is a function that is trained using the features of users and topological structures of social networks. The function can map the observed ＂corrupted＂ matrix to an ＂uncorrupted＂ matrix（target matrix）. We performed community detection using the target matrix, which is better than using the original matrix. Five real networks are processed with this algorithm. The results show that SJDM algorithm is more efficient compared to the other four algorithms.

关 键 词：社交网络分析 预测 监督学习 社区网络 矩阵“去噪” 弱大数定律 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]