基于聚类的超链路预测  

Clustering-based hyperlink prediction

作　　者：齐鹏飞 周丽华[1] 杜国王 黄皓 黄通 QI Pengfei;ZHOU Lihua;DU Guowang;HUANG Hao;HUANG Tong(School of Information,Yunnan University,Kunming Yunnan 650091,China)

机构地区：[1]云南大学信息学院

出　　处：《计算机应用》2020年第2期434-440,共7页journal of Computer Applications

基　　金：国家自然科学基金资助项目(61762090,61262069,61966036,61662086);云南省自然科学基金资助项目(2016FA026);云南省创新研究团队项目(2018HC019);云南省高等学校科技创新团队项目(IRTSTYN);云南省教育厅基金资助项目(2019Y0006)~~

摘　　要：超链路预测是利用已观测到网络的特性来复现网络中缺失的链路。现有的超链路预测算法通常利用整个网络来进行预测,预测结果会遗漏训练样本数据较少的链路类别,导致预测种类不够全面。为了解决这个问题,提出了基于聚类的超链路预测算法C-CMM,首先对数据集进行聚类分簇,进而对每一个簇建立模型进行超链路预测。所提算法能够充分利用各个簇的观察样本所蕴含的信息,扩大预测结果覆盖的类别。在三个真实数据集上的实验结果表明,C-CMM和多个先进的链路预测算法相比具有更高的预测精度和效率,同时其预测覆盖种类也更加全面。Hyperlink prediction aims to utilize inherent properties of observed network to reproduce the missing links in the network.Existing hyperlink prediction algorithms often make predictions based on entire network,and some link types with insufficient training samples data may be missed,resulting in imcomplete link types to be detected.To address this problem,a clustering-based hyperlink prediction algorithm named C-CMM was proposed.Firstly,the dataset was divided into clusters,and then the model was constructed for each cluster to perform hyperlink prediction.The proposed algorithm can make full use of the information contained in the observation samples of each cluster,and widen the coverage range of the prediction results.Experimental results on three real-world datasets show that the proposed algorithm outperforms a great number of state-of-the-art link prediction algorithms in prediction accuracy and efficiency,and has the prediction coverage more comprehensive.

关 键 词：信息网络 超链路预测 聚类 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]