A knowledge graph embedding method based on a diverse graph attention mechanism

Abstract

The invention provides a knowledge graph embedding method based on a diverse graph attention mechanism, and the method comprises the following steps: 1, carrying out the preprocessing of knowledge graph data, and enabling a traditional knowledge graph to be preprocessed into structured data according to model requirements; 2, establishing an entity attention mechanism, wherein the entity attentionmechanism establishing mode is that the vector representation of an entity is learned on an adjacent graph by using n attention heads and self-attention through using a diverse graph attention mechanism; Step 3, establishing a relation attention mechanism in which the vector representation of the entity on the relation graph is learned by using n attention heads and self-attention by using a diverse graph attention mechanism; Step 4, carrying out modeling of multi-relation data in the relation graph; And 5, carrying out model training to obtain vectorized representations of all relationshipsin the knowledge graph.

Description

technical field [0001] The present invention relates to a knowledge graph embedding method, in particular to a knowledge graph embedding method based on a diverse graph attention mechanism. Background technique [0002] In 2012, Google proposed the concept of knowledge graph, which is essentially a knowledge base represented by a graph structure. Existing common knowledge graphs include but are not limited to Freebase, DBPedia, and YAGO. Multi-relational data stored in knowledge graphs have been applied as a set of prior rules or constraints in a large number of machine learning tasks, such as information retrieval, question answering systems, and natural language processing. To facilitate and standardize knowledge application in downstream tasks, several works attempt to model these data in a more computable form. Among them, many knowledge graph embedding methods have been widely studied and focused on. [0003] Usually, knowledge in a knowledge graph is stored as a sta...

AI Technical Summary

Problems solved by technology

However, existing techniques still focus on learning knowledge graph embeddings in a simple and intuitive way without considering the knowledge context

Images