Relational Graph Convolutional Networks: A Closer Look

TL;DR

This paper reproduces and explains the Relational Graph Convolutional Network (RGCN), validating its correctness on benchmark datasets, and introduces two more parameter-efficient configurations for improved performance.

Contribution

It provides a detailed reproduction and explanation of RGCN, along with two novel, more efficient configurations of the model.

Findings

Empirically validated RGCN correctness on benchmark datasets.

Provided a clear understanding of RGCN components.

Introduced two new parameter-efficient RGCN configurations.

Abstract

In this paper, we describe a reproduction of the Relational Graph Convolutional Network (RGCN). Using our reproduction, we explain the intuition behind the model. Our reproduction results empirically validate the correctness of our implementations using benchmark Knowledge Graph datasets on node classification and link prediction tasks. Our explanation provides a friendly understanding of the different components of the RGCN for both users and researchers extending the RGCN approach. Furthermore, we introduce two new configurations of the RGCN that are more parameter efficient. The code and datasets are available at https://github.com/thiviyanT/torch-rgcn.