NE-GCN: Advancing Knowledge Graph Link Prediction with Node2vec-Enhanced Graph Convolutional Networks

Knowledge graphs (KGs) play a vital role in enhancing search results and recommendationsystems. With the rapid increase in the size of the KGs, they are becoming inaccuracy andincomplete. This problem can be solved by the knowledge graph completion methods. In this paperwe use a novel method for knowledge graph link prediction named Node2vec Enhanced GraphConvolutional Network (NE-GCN), for computing pairwise occurrences of entity-relation pairs inthe dataset to construct a joint learning model. Given a knowledge graph, NE-GCN constructs asingle graph considering entities and relations as individual nodes. NE-GCN then computesweights for edges among nodes based on the pairwise occurrence of entities and relations. Next,uses Graph Convolution neural Network (GCN) to update vector representations for entity andrelation nodes. This work opens up new possibilities for graph-based learning models andrepresents a major leap in the field.

NE-GCN: Advancing Knowledge Graph Link Prediction with Node2vec-Enhanced Graph Convolutional Networks Keywords:

Knowledge graph , Linkprediction , Node2vec , Graphconvolutional network