TransAlign: Fully Automatic and Effective Entity Alignment for Knowledge Graphs

TL;DR

TransAlign is a fully automatic method for entity alignment in knowledge graphs that does not require manual seed alignments, using predicate proximity graphs and attribute-based entity embedding alignment to improve accuracy.

Contribution

It introduces the first fully automatic entity alignment approach that eliminates the need for manually crafted seed alignments, enhancing efficiency and effectiveness.

Findings

Significantly outperforms state-of-the-art methods in accuracy.

Automatically captures predicate similarities without manual seeds.

Effectively aligns entities using attribute-based embedding shifts.

Abstract

The task of entity alignment between knowledge graphs (KGs) aims to identify every pair of entities from two different KGs that represent the same entity. Many machine learning-based methods have been proposed for this task. However, to our best knowledge, existing methods all require manually crafted seed alignments, which are expensive to obtain. In this paper, we propose the first fully automatic alignment method named TransAlign, which does not require any manually crafted seed alignments. Specifically, for predicate embeddings, TransAlign constructs a predicate-proximity-graph to automatically capture the similarity between predicates across two KGs by learning the attention of entity types. For entity embeddings, TransAlign first computes the entity embeddings of each KG independently using TransE, and then shifts the two KGs' entity embeddings into the same vector space by computing the similarity between entities based on their attributes. Thus, both predicate alignment and entity alignment can be done without manually crafted seed alignments. TransAlign is not only fully automatic, but also highly effective. Experiments using real-world KGs show that TransAlign improves the accuracy of entity alignment significantly compared to state-of-the-art methods.