Knowledge graph joint representation learning method fusing graph convolution and translation model

Abstract

The invention discloses a knowledge graph joint representation learning method fusing graph convolution and a translation model. The knowledge graph joint representation learning method comprises the following steps of 1) constructing a direct adjacency matrix and an indirect adjacency matrix corresponding to a knowledge graph according to the knowledge graph; 2) designing a drawing convolutional network which comprises an input layer, two hidden layers and an output layer, optimizing the attention coefficients of the adjacent point nodes to a central node, and obtaining the vector representation of the nodes by learning the structure information of the direct adjacent nodes and the indirect adjacent nodes; 3) learning the semantic information of the relationship by adopting a translation model to obtain the vector representation of an entity and the relationship; and 4) fusing the graph convolutional network and the translation model, and obtaining the final vector representation of the knowledge graph through the continuous iterative learning. According to the present invention, the structure information and the relation semantics of the knowledge graph can be learned at the same time, and the vector representation precision of the knowledge graph is improved.

Description

technical field [0001] The invention relates to the fields of knowledge graphs, representation learning, etc., and in particular provides a knowledge graph joint representation learning method that integrates graph convolution and translation models. Background technique [0002] Knowledge graph representation learning aims to map the entities and relationships of knowledge graphs from a high-dimensional discrete space to a continuous low-dimensional vector space while retaining the original semantic information by learning the semantic features in the knowledge graph, so that Entities and relationships can be directly numerically calculated to improve computational efficiency. [0003] The existing main knowledge graph representation learning models include translation models, semantic matching models and neural network models. The main idea of ​​the translation model is to interpret the relationship r in the triplet (h, r, t) as the translation process from the head entit...

AI Technical Summary

Problems solved by technology

[0004] However, existing methods usually only focus on a certain aspect of the knowledge graph, such as structural features and relational features, and cannot fully learn the knowledge graph structure and semantic information, resulting in low accuracy of knowledge graph representation learning results.

Images