Entity alignment method based on heterogeneous graph attention network

Abstract

The invention discloses an entity alignment method based on a heterogeneous graph attention network, and the method comprises the steps: dividing entities into different categories based on clustering; secondly, learning an embedded vector of an entity based on the heterogeneous graph attention network; calculating the similarity between different entity categories based on entity embedded vectors, and obtaining the similarity of any entity pair by combining the vector similarity; and finally, modeling an entity alignment problem into an integer programming problem, and solving and obtaining an alignment result meeting a one-to-one alignment constraint. The method is not only low in time complexity, but also high in entity alignment precision.

Description

technical field [0001] The invention belongs to the field of knowledge fusion, and in particular relates to an entity alignment method based on a heterogeneous graph attention network related to entity alignment. Background technique [0002] With the expansion of the scale of knowledge bases and the increase of the number of entities, the importance of entity links between different knowledge bases has become increasingly prominent, and entity alignment of multi-knowledge graphs has become a hot research direction. [0003] The current entity alignment-related technologies and methods are derived from entity matching in the database. However, in practical applications, there are many problems and challenges, the most prominent of which are the problems of computational complexity and data alignment quality. Under the condition of big data, the amount of data in the knowledge base is huge and complicated, the traditional entity alignment algorithm has high time complexity, a...

AI Technical Summary

Problems solved by technology

[0003] The current entity alignment related technologies and methods are derived from entity matching in the database. However, in practical applications, there are many problems and challenges, the most prominent of which are the problems of computational complexity and data alignment quality.

Under the condition of big data, the amount of data in the knowledge base is huge and complicated, the traditional entity alignment algorithm has high time complexity, and the accuracy of entity alignment is insufficient

Images