Composition-based Multi-Relational Graph Convolutional Networks
This addresses the limitations of existing methods for multi-relational graphs, which suffer from over-parameterization and only learn node representations, benefiting researchers and practitioners in graph-based machine learning.
The paper tackled the problem of modeling multi-relational graphs, which are more general than simple undirected graphs, by proposing CompGCN, a Graph Convolutional framework that jointly embeds nodes and relations, achieving demonstrably superior results on tasks like node classification, link prediction, and graph classification.
Graph Convolutional Networks (GCNs) have recently been shown to be quite successful in modeling graph-structured data. However, the primary focus has been on handling simple undirected graphs. Multi-relational graphs are a more general and prevalent form of graphs where each edge has a label and direction associated with it. Most of the existing approaches to handle such graphs suffer from over-parameterization and are restricted to learning representations of nodes only. In this paper, we propose CompGCN, a novel Graph Convolutional framework which jointly embeds both nodes and relations in a relational graph. CompGCN leverages a variety of entity-relation composition operations from Knowledge Graph Embedding techniques and scales with the number of relations. It also generalizes several of the existing multi-relational GCN methods. We evaluate our proposed method on multiple tasks such as node classification, link prediction, and graph classification, and achieve demonstrably superior results. We make the source code of CompGCN available to foster reproducible research.