Relational Graph Convolutional Networks: A Closer Look
This work provides a clearer understanding and improved efficiency for researchers and users working with RGCNs, but it is incremental as it builds on an existing method.
The paper reproduces the Relational Graph Convolutional Network (RGCN) to validate its correctness on benchmark knowledge graph tasks and introduces two more parameter-efficient configurations.
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.