Heterogeneous network node representation learning method based on meta-path

Abstract

The invention provides a heterogeneous network node representation learning method based on a meta-path. According to the method, various node types and relationship types contained in a heterogeneousnetwork graph are considered, and rich semantic information and structure information in the network graph are stored in a plurality of meta-paths in a meta-path extraction mode. In each meta-path, the feature information of the nodes in the meta-path is saved by learning the vector representation of the nodes, and then the plurality of meta-paths are integrated together for common training, so that the semantic information and the structure information in the whole heterogeneous network are saved in the node vector representation. The method has higher classification accuracy, the feature information of the nodes in the heterogeneous network can be better stored in the vector representation of the nodes, the meta-paths can be freely selected according to specific target tasks, and the method is more flexible.

Description

technical field [0001] The invention belongs to the technical field of graph representation learning, and more specifically, relates to a meta-path-based heterogeneous network node representation learning method. Background technique [0002] Today, network diagrams are a common form of data organization. More and more applications in the real world store and present data in the form of network graphs. For example, the social network graph formed by Facebook and twitter, the paper citation network built on DBLP, the network formed between protein molecules in biology, etc. In order to mine the valuable information hidden in the network graph, it is necessary to convert the network graph into a form that can be processed by machine learning, so network representation learning becomes a key step. [0003] Compared with homogeneous network graphs containing only one node type and relationship, heterogeneous network graphs usually contain multiple types of nodes and relationsh...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is how to store the rich semantic information and structural information contained in the heterogeneous network graph in the vector representation of the nodes, so as to overcome the problem of the existing network representation learning methods for the network containing multiple node types and relationship types. Insufficient Processing Capability of Complex Heterogeneous Network Graphs

Images