多层网络链路预测研究进展  

ADVANCES OF LINK PREDICTION IN MULTILAYER NETWORKS

作　　者：王飞程 周钰颖 闵勇[1] Wang Feicheng;Zhou Yuying;Min Yong(College of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,Zhejiang,China)

机构地区：[1]浙江工业大学计算机科学与技术学院,浙江杭州310023

出　　处：《计算机应用与软件》2021年第5期10-20,共11页Computer Applications and Software

基　　金：浙江省自然科学基金项目(LY17G030030,LGF18D010001,LGF18D010002)。

摘　　要：链路预测是指通过已知的信息预测网络中尚未连边的两个节点之间产生连接的可能性。如今存在大量单层网络的链路预测方法,多层网络链路预测问题在近三年为人所重视,但较少有人进行系统整理。针对该问题,对现有多层网络链路预测算法进行归纳和对比,主要分为基于单层链路预测扩展的方法、建立模型的方法和基于机器学习的方法。第一类方法利用其他层层间关系和层内关系预测目标层信息;第二类方法构建模型;第三类方法提取层间和层内特征,使用机器学习完成链路预测。Link prediction refers to the possibility of predicting the connection between two nodes in the network that are not connected to each other through known information.Nowadays,there are a lot of link prediction methods for single-layer networks.The problem of link prediction for multi-layer networks has attracted much attention in recent three years,but few people systematically collate it.Aiming at this problem,this paper summarizes and compares the existing link prediction algorithms of multilayer networks,which are mainly divided into the methods based on single-layer link prediction,modeling methods and the methods based on machine learning.In the first method,target layer information is predicted by other interlayer information and intralayer information.The second method needs to build a model.The third method uses machine learning to extract interlayer and intralayer features to complete link prediction.

关 键 词：多层网络 链路预测 层间关系 层内关系 机器学习 

分 类 号：TP3-0[自动化与计算机技术—计算机科学与技术]