摘要
针对社会网络中新关系出现的预测,提出一种基于自动学习机的社会网络链路预测算法。将自动学习机与三元组转化相结合,将不同类型三元组的转化作为预测的重要依据并构造学习函数,提出六种三元组内节点相似性指标。实验结果表明,该算法所提出的六个预测指标的预测准确度和稳定性要好于六种常用的链路预测指标,对于社会网络分析具有实际应用价值。
For grasping the law of emergence,this paper proposed a novel link prediction algorithm which based on learning automata.The algorithm combined learning automata with transformations of tri-motifs for the first time,and constructed a learning function;proposed an inter tri-motifs similarity index.The experimental results showed that the accuracy and stability of the proposed algorithm were better than six commonly used link prediction indexes.The proposed algorithm has practical application value in social network analysis.
作者
卢文
赵海兴
卫良
李发旭
Lu Wen;Zhao Haixing;Wei Liang;Li Faxu(College of Computer Science,Shaanxi Normal University,Xi’an 710119,Shaanxi,China;College of Computer,Qinghai Normal University,Xining 810008,Shaanxi,China;Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province,Xining 810008,Shaanxi,China;Key Laboratory of Tibetan Information Processing Ministry of Education,Xining 810008,Shaanxi,China)
出处
《计算机应用与软件》
北大核心
2022年第1期242-249,共8页
Computer Applications and Software
基金
国家自然科学基金项目(11661069,61663041,61763041)
教育部春晖项目(Z2016101)
藏文信息处理与机器翻译重点实验项目(2013-Z-Y17)
青海省科技厅项目(2018-ZJ-718)。
关键词
社会网络
自动学习机
三元组
链路预测
Social network
Learning automata
Tri-motif
Link prediction
