A Benchmark and Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning

TL;DR

This paper surveys entity alignment methods in knowledge graphs using representation learning, introduces new datasets, and analyzes factors affecting performance, highlighting the importance of attribute triples and relation predicates.

Contribution

It provides a comprehensive framework, new benchmark datasets, and extensive experiments to evaluate and understand entity alignment techniques.

Findings

Attribute triples and relation predicates significantly improve performance.

New datasets address limitations of existing benchmarks.

Empirical results highlight key factors influencing technique effectiveness.

Abstract

In the last few years, the interest in knowledge bases has grown exponentially in both the research community and the industry due to their essential role in AI applications. Entity alignment is an important task for enriching knowledge bases. This paper provides a comprehensive tutorial-type survey on representative entity alignment techniques that use the new approach of representation learning. We present a framework for capturing the key characteristics of these techniques, propose two datasets to address the limitation of existing benchmark datasets, and conduct extensive experiments using the proposed datasets. The framework gives a clear picture of how the techniques work. The experiments yield important results about the empirical performance of the techniques and how various factors affect the performance. One important observation not stressed by previous work is that techniques making good use of attribute triples and relation predicates as features stand out as winners.