Multisource Heterogeneous Graph Big Data Representation Learning

The large amount of accumulated and complex data also brings challenges to query and processing. With the update of data, the number of nodes and edges contained in the graph may become larger and larger. The number of nodes in large-scale graph structure data can reach millions or even hundreds of millions, and presents the characteristics of multisource, heterogeneity, isomerization and dynamics.Multisource heterogeneous big data can often be modeled into a graph data structure with representation learning. The complex network graph normally has certain particularity, which increases the difficulty of research. Large-scale complex heterogeneous graph data representation learning model has a wide range of applications in many fields. This book addresses these multisource heterogeneous graph big data representation learning models as well as their applications in the field of public security.