Knowledge Graph Entity Alignment with Graph Convolutional Networks: Lessons Learned

TL;DR

This paper critically examines GCN-based models for knowledge graph entity alignment, highlighting implementation discrepancies, necessary tricks for model success, and providing a comprehensive evaluation of datasets and methods.

Contribution

It offers an in-depth analysis of GCN-based entity alignment, revealing implementation issues, essential techniques, and systematizing benchmark datasets for improved understanding.

Findings

Implementation differences affect results significantly

Certain tricks are crucial for model performance

Benchmark datasets vary in difficulty and suitability

Abstract

In this work, we focus on the problem of entity alignment in Knowledge Graphs (KG) and we report on our experiences when applying a Graph Convolutional Network (GCN) based model for this task. Variants of GCN are used in multiple state-of-the-art approaches and therefore it is important to understand the specifics and limitations of GCN-based models. Despite serious efforts, we were not able to fully reproduce the results from the original paper and after a thorough audit of the code provided by authors, we concluded, that their implementation is different from the architecture described in the paper. In addition, several tricks are required to make the model work and some of them are not very intuitive. We provide an extensive ablation study to quantify the effects these tricks and changes of architecture have on final performance. Furthermore, we examine current evaluation approaches and systematize available benchmark datasets. We believe that people interested in KG matching might profit from our work, as well as novices entering the field