PRGNN: Modeling high-order proximity with relational graph neural network for knowledge graph completion

Relational Graph Neural Networks (RGNNs) are designed to extract structural information from relational graphs and have garnered attention in the domain of Knowledge Graph Completion (KGC). However, recent empirical investigations have indicated that some prominent RGNN-based methodologies have not significantly enhanced precision, prompting questions regarding the efficacy of RGNNs in KGC applications. In this paper, we introduce a novel RGNN-based KGC approach, the Proximity Relational Graph Neural Network (PRGNN), which excels at modeling high -order proximities among entities. PRGNN is founded on a notably straightforward yet effective RGNN framework that discards unnecessary components commonly incorporated in previous approaches, such as attention layers, and linear and non-linear mappings. We demonstrate that PRGNN empowers traditional KGC techniques to apprehend high -order proximities among entities more effectively. Through extensive experimentation on benchmark datasets, we establish that PRGNN consistently outperforms conventional KGC methods and achieves state-of-the-art results. Furthermore, we show that PRGNN necessitates considerably less training time (ranging from one-third to one -fifth) and fewer parameters (ranging from half to two-thirds), rendering it an exceptionally efficient approach. All data and code have been made available at 1 .