Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning models.However,any metapath...Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning models.However,any metapaths consisting of multiple,simple metarelations must be driven by domain experts.These sensitive,expensive,and limited metapaths severely reduce the flexibility and scalability of the existing models.A metapath-free,scalable representation learning model,called Metarelation2vec,is proposed for HNs with biased joint learning of all metarelations in a bid to address this problem.Specifically,a metarelation-aware,biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given metapaths.Thereafter,grouped nodes by the type,a common and shallow skip-gram model is used to separately learn structural proximity for each node type.Next,grouped links by the type,a novel and shallow model is used to separately learn the semantic proximity for each link type.Finally,supervised by the cooperation probabilities of all meta-words,the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs,ensuring the accuracy and scalability of the models.Extensive experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.展开更多
Heterogeneous information network(HIN)has recently been widely adopted to describe complex graph structure in recommendation systems,proving its effectiveness in modeling complex graph data.Although existing HIN-based...Heterogeneous information network(HIN)has recently been widely adopted to describe complex graph structure in recommendation systems,proving its effectiveness in modeling complex graph data.Although existing HIN-based recommendation studies have achieved great success by performing message propagation between connected nodes on the defined metapaths,they have the following major limitations.Existing works mainly convert heterogeneous graphs into homogeneous graphs via defining metapaths,which are not expressive enough to capture more complicated dependency relationships involved on the metapath.Besides,the heterogeneous information is more likely to be provided by item attributes while social relations between users are not adequately considered.To tackle these limitations,we propose a novel social recommendation model MPISR,which models MetaPath Interaction for Social Recommendation on heterogeneous information network.Specifically,our model first learns the initial node representation through a pretraining module,and then identifies potential social friends and item relations based on their similarity to construct a unified HIN.We then develop the two-way encoder module with similarity encoder and instance encoder to capture the similarity collaborative signals and relational dependency on different metapaths.Extensive experiments on five real datasets demonstrate the effectiveness of our method.展开更多
现有的异构图嵌入学习方法存在两个方面的问题,一是没有考虑不同节点属性间的深层联系,二是通过注意力机制聚合邻居节点来生成目标节点的向量表示,忽略了目标节点的特征在向量表示中起的作用。为解决上述问题,本文提出了一种多重注意力...现有的异构图嵌入学习方法存在两个方面的问题,一是没有考虑不同节点属性间的深层联系,二是通过注意力机制聚合邻居节点来生成目标节点的向量表示,忽略了目标节点的特征在向量表示中起的作用。为解决上述问题,本文提出了一种多重注意力指导下的异构图神经网络,从点-线-网3个角度学习异构节点嵌入向量。使用双向长短期记忆模型(bidirectional long short-term memory networks,Bi-LSTM)挖掘不同节点的属性间的深层关联关系并将其映射到同一向量空间,利用级联网络对单条元路径实例上的邻居节点和目标节点的特征信息进行融合,从而增强嵌入向量对目标节点信息的表达能力,提出一种多重注意力机制来聚合多条元路径实例上的节点信息,生成最终的节点嵌入向量表示。在3个大型异构图上的实验结果表明,本文提出的模型在异构图嵌入的效果方面优于现有基线模型,并且对于增强节点属性信息上的表达展现出了良好的性能。展开更多
基金supported by the National Key Research and Development Program(No.2019YFE0105300)the National Natural Science Foundation of China(No.62103143)+2 种基金the Hunan Province Key Research and Development Program(No.2022WK2006)the Special Project for the Construction of Innovative Provinces in Hunan(Nos.2020TP2018 and 2019GK4030)the Scientific Research Fund of Hunan Provincial Education Department(No.22B0471).
文摘Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning models.However,any metapaths consisting of multiple,simple metarelations must be driven by domain experts.These sensitive,expensive,and limited metapaths severely reduce the flexibility and scalability of the existing models.A metapath-free,scalable representation learning model,called Metarelation2vec,is proposed for HNs with biased joint learning of all metarelations in a bid to address this problem.Specifically,a metarelation-aware,biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given metapaths.Thereafter,grouped nodes by the type,a common and shallow skip-gram model is used to separately learn structural proximity for each node type.Next,grouped links by the type,a novel and shallow model is used to separately learn the semantic proximity for each link type.Finally,supervised by the cooperation probabilities of all meta-words,the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs,ensuring the accuracy and scalability of the models.Extensive experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.
基金supported by the National Natural Science Foundation of China(Grant Nos.61762078,62276073,61966009 and U22A2099)the Industrial Support Project of Gansu Colleges(No.2022CYZC11)+3 种基金the Natural Science Foundation of Gansu Province(21JR7RA114)the Northwest Normal University Young Teachers Research Capacity Promotion Plan(NWNU-LKQN2019-2)the Industrial Support Project of Gansu Colleges(No.2022CYZC11)the Northwest Normal University Post-graduate Research Funding Project(2021KYZZ02107).
文摘Heterogeneous information network(HIN)has recently been widely adopted to describe complex graph structure in recommendation systems,proving its effectiveness in modeling complex graph data.Although existing HIN-based recommendation studies have achieved great success by performing message propagation between connected nodes on the defined metapaths,they have the following major limitations.Existing works mainly convert heterogeneous graphs into homogeneous graphs via defining metapaths,which are not expressive enough to capture more complicated dependency relationships involved on the metapath.Besides,the heterogeneous information is more likely to be provided by item attributes while social relations between users are not adequately considered.To tackle these limitations,we propose a novel social recommendation model MPISR,which models MetaPath Interaction for Social Recommendation on heterogeneous information network.Specifically,our model first learns the initial node representation through a pretraining module,and then identifies potential social friends and item relations based on their similarity to construct a unified HIN.We then develop the two-way encoder module with similarity encoder and instance encoder to capture the similarity collaborative signals and relational dependency on different metapaths.Extensive experiments on five real datasets demonstrate the effectiveness of our method.
文摘现有的异构图嵌入学习方法存在两个方面的问题,一是没有考虑不同节点属性间的深层联系,二是通过注意力机制聚合邻居节点来生成目标节点的向量表示,忽略了目标节点的特征在向量表示中起的作用。为解决上述问题,本文提出了一种多重注意力指导下的异构图神经网络,从点-线-网3个角度学习异构节点嵌入向量。使用双向长短期记忆模型(bidirectional long short-term memory networks,Bi-LSTM)挖掘不同节点的属性间的深层关联关系并将其映射到同一向量空间,利用级联网络对单条元路径实例上的邻居节点和目标节点的特征信息进行融合,从而增强嵌入向量对目标节点信息的表达能力,提出一种多重注意力机制来聚合多条元路径实例上的节点信息,生成最终的节点嵌入向量表示。在3个大型异构图上的实验结果表明,本文提出的模型在异构图嵌入的效果方面优于现有基线模型,并且对于增强节点属性信息上的表达展现出了良好的性能。
