随着在线社交网络的普及,基于位置的社交网络(Location-Based Social Networks,LBSN)积累了海量数据,且因其包含丰富的时空、语义信息已被广泛应用在挖掘用户行为偏好的研究上,但传统的手工提取LBSN特征的方法有很大局限性且耗时耗力....随着在线社交网络的普及,基于位置的社交网络(Location-Based Social Networks,LBSN)积累了海量数据,且因其包含丰富的时空、语义信息已被广泛应用在挖掘用户行为偏好的研究上,但传统的手工提取LBSN特征的方法有很大局限性且耗时耗力.近几年来,图表示学习在推荐系统、知识图谱等领域成功应用,彰显了其强大的非线性拟合和表示学习的能力.然而,现有图表示学习大多集中在静态、同构的网络上,难以同时考虑时间、位置信息、社交关系来捕捉LBSN中复杂的结构和用户偏好,以致无法高效提取LBSN中的有效信息.因此,本文提出面向LBSN的两阶段图表示学习框架TGE-LBSN(Two Stages of Graph Embedding on LBSN),即将LBSN转化成异构网络结构,设计了LBSN上的图表示学习算法自动提取LBSN的特征,得到蕴含有效信息的节点向量表示,并利用社交领域的预测、推荐任务检验其有效性.首先,依据时间对LBSN的签到(Check-in)超边进行有偏采样,第一阶段设计了IVGS(Initial Vector Generation Stage)算法,利用好友边与Check-in超边共同生成包含位置、特征信息的初始节点向量.其次,在第二阶段将LBSN依据签到时间划分成不同子图,分别进行各个子图下的异构网络层结构信息聚合操作.在第一阶段结果的基础上,提出了面向LBSN的选择聚合邻居策略SAN(Select Aggre⁃gated Neighbors),选取有代表性的邻居节点完成聚合操作,进而完成子图向量生成算法SVG(Subgraph Vector Generation)得到子图中节点的向量表示.最后,依据任务设定损失函数,结合注意力机制为各子图学得自适应权重,从而得到节点的最终向量表示,进而完成社交领域的预测推荐任务.本研究分别在真实的LBSN数据集上以及时序社交网络与基准方法进行了大量的对比实验,并采用ROC曲线作为评价标准,实验结果验证了本文所提算法TGE-LBSN能高效地自动提取LBSN的有效信息并保留在节点的嵌入向量中,且在社交领域的好友预测任务上比现有模型在AUC值方面最高可提升42%,在兴趣点推荐任务上AUC取值相较于对比算法最高可达到7%的提升.展开更多
Potential behavior prediction involves understanding the latent human behavior of specific groups,and can assist organizations in making strategic decisions.Progress in information technology has made it possible to a...Potential behavior prediction involves understanding the latent human behavior of specific groups,and can assist organizations in making strategic decisions.Progress in information technology has made it possible to acquire more and more data about human behavior.In this paper,we examine behavior data obtained in realworld scenarios as an information network composed of two types of objects(humans and actions)associated with various attributes and three types of relationships(human-human,human-action,and action-action),which we call the heterogeneous behavior network(HBN).To exploit the abundance and heterogeneity of the HBN,we propose a novel network embedding method,human-action-attribute-aware heterogeneous network embedding(a4 HNE),which jointly considers structural proximity,attribute resemblance,and heterogeneity fusion.Experiments on two real-world datasets show that this approach outperforms other similar methods on various heterogeneous information network mining tasks for potential behavior prediction.展开更多
基金Project supported by the National Natural Science Foundation of China(Nos.U1509206,61625107,and U1611461)the Key Program of Zhejiang Province,China(No.2015C01027).
文摘Potential behavior prediction involves understanding the latent human behavior of specific groups,and can assist organizations in making strategic decisions.Progress in information technology has made it possible to acquire more and more data about human behavior.In this paper,we examine behavior data obtained in realworld scenarios as an information network composed of two types of objects(humans and actions)associated with various attributes and three types of relationships(human-human,human-action,and action-action),which we call the heterogeneous behavior network(HBN).To exploit the abundance and heterogeneity of the HBN,we propose a novel network embedding method,human-action-attribute-aware heterogeneous network embedding(a4 HNE),which jointly considers structural proximity,attribute resemblance,and heterogeneity fusion.Experiments on two real-world datasets show that this approach outperforms other similar methods on various heterogeneous information network mining tasks for potential behavior prediction.
