Enhanced network representation learning method based on community perception and relationship attention

Abstract

The invention provides an enhanced network representation learning method based on community perception and relationship attention, and the method comprises the following steps: firstly obtaining a network topology structure and the text information of a node; secondly, acquiring community information by adopting a community discovery algorithm, marking a community where each node is located, andcombining the community with the topological structure to generate a community structure network; then, learning structure embedding of nodes on the community structure network by adopting a communityperception module; then, learning text embedding of each pair of adjacent nodes by adopting a relation attention module; and finally, performing model training in combination with structure embeddingand text embedding to obtain embedded representation of each node. According to the invention, local and global structures of the network and rich semantic relationships among nodes can be completelycaptured.

Description

technical field [0001] The present invention relates to a network representation learning, and more specifically, to a method for enhancing network representation learning based on community awareness and relational attention. Background technique [0002] Networks are widely used data formats in real-world scenarios, such as social networks in social media, protein interaction networks in biological sciences, and citation networks in research fields. Due to the ubiquity of the network, the analysis of the network has attracted more and more attention. However, the real-world network has sparsity and huge data volume, how to convert each node in the network into a low-dimensional latent representation has become a major research problem. To solve this problem, network representation learning is proposed. Network representation learning, as an upstream task of complex network reasoning, aims to study how to preserve network structural features and rich attribute information...

AI Technical Summary

Problems solved by technology

[0006] The problem to be solved by the present invention is to provide a method for enhancing network representation learning based on community awareness and relational attention in view of the above-mentioned deficiencies in the prior art, which solves the inability to completely capture the local and global structure of the network in the prior art and the problem of rich semantic relationships between nodes

Images