From Uni-relational to Multi-relational Graph Neural Networks

Graph Neural Networks (GNNs), which extend deep neural networks to graph-structured data, have attracted increasing attention. They have been proven to be powerful for numerous graph related tasks that cover a variety of research areas including natural language processing, information retrieval and knowledge graph completion (KGC). GNNs are primary designed for simple homogeneous and uni-relational graphs. Due to its great success in handling the graph data, considerable studies have been developed to extend GNNs to process complex multi-relational graphs such as the knowledge graph. My research first focuses on learning effective representation of uni-relational graph to facilitate some downstream applications such as graph classification and query understanding, and show the great capacity of GNNs to advance these tasks. Although the GNNs have demonstrated its significant effectiveness on the uni-relational graph in a large range of applications, we surprisingly found it may not be as crucial as previously believed in the knowledge graph completion task. It suggests careful attention to more suitable GNNs designs for KGC task.