一种面向动态异构信息网络的高效极大motif团挖掘方法

An Efficient and Large Motif Group Mining Method Oriented to Dynamic Heterogeneous Information Network

异构信息网络是一种把顶点与类型标签相关联的数据图,用于刻画不同类型对象间的复杂限制语义,如地理社交网络和生物网络等。给定不同类型顶点间的限制关系,极大motif团是符合这种限制关系的“完全子图”。通过发现极大motif团可以在异构信息网络上找到满足特定限制关系且关联紧密的群体。考虑到实际应用中异构信息网络频繁更新,且现有的极大motif团挖掘算法不支持动态图上极大motif团的高效挖掘问题,本文通过设计新的加边、减边策略,提出了一种支持极大motif团更新的算法UMMD。基于多个真实数据集的实验结果表明,UMMD算法具有高效性。

Heterogeneous information network is a data graph that associates vertices with type labels,which is used to describe complex restriction semantics between different types of objects,such as geographic social networks and biological networks.Given the restriction relationship between different types of vertices,the maximal motif clique is a“holistic subgraph”that conforms to this restriction relationship.By discovering maximal motif cliques,it is possible to find closely related groups that meet specific restricted relationships on heterogeneous information networks.Considering that heterogeneous information networks are frequently updated in practical applications,and the existing maximal motif clique mining algorithm does not support the efficient mining of maximal motif clique on dynamic graphs,this paper proposes a new edge addition and reduction strategy by designing An algorithm UMMD that supports the update of maximal motif clique.Experimental results based on multiple real data sets show that the UMMD algorithm is highly efficient.