Thanapalasingam Thiviyan, van Berkel Lucas, Bloem Peter, Groth Paul
University of Amsterdam, Amsterdam, Noord Holland, Netherlands.
VU University Amsterdam, Amsterdam, Noord Holland, Netherlands.
PeerJ Comput Sci. 2022 Nov 2;8:e1073. doi: 10.7717/peerj-cs.1073. eCollection 2022.
In this article, 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.
在本文中，我们描述了关系图卷积网络（RGCN）的一种复现。通过我们的复现，我们解释了该模型背后的直觉。我们的复现结果通过在节点分类和链接预测任务中使用基准知识图谱数据集，从经验上验证了我们实现的正确性。我们的解释为用户和扩展RGCN方法的研究人员提供了对RGCN不同组件的友好理解。此外，我们引入了两种参数效率更高的RGCN新配置。代码和数据集可在https://github.com/thiviyanT/torch-rgcn获取。
