Rule-Guided Joint Embedding Learning of Knowledge Graphs

In recent studies, the focus has been on enhancing knowledge graph embedding learning, which encodes entities and relations in knowledge graphs into low-dimensional vector spaces. While current models mainly consider the structural aspects of these graphs, there's a wealth of contextual and literal information in knowledge graphs that can be utilized for more effective embeddings. This paper introduces a novel model that incorporates both contextual and literal information into entity and relation embeddings, utilizing graph convolutional networks. Specifically, for contextual information, we assess its significance through confidence and relatedness metrics. A unique rule-based method is developed to calculate the confidence metric, and the relatedness metric is derived from the literal information's representations. We validated our model's performance with thorough experiments on two established benchmark datasets.