Graph Attention Network Knowledge Graph Completion Model Based on Relational Aggregation

Knowledge Graph Completion (KGC) refers to inferring missing links based on existing triples. Research has found that graph neural networks perform well in this task. By using the topology of the graph and the characteristics of the nodes to learn, the feature representation of the nodes can be updated, and more semantic information can be obtained from the surrounding entities and relationships. This paper aims to propose an end-to-end structured Graph Attention Network Enhanced Relationship Aggregation (GANERA) knowledge graph completion model. Firstly, entity aggregation is performed on the central entity by adding an entity attention mechanism. The addition of entity attention can distinguish the importance of different neighbor entities and screen more important entity embeddings. At the same time, the expression ability of the message function is enhanced through specific relational parameters, so that the model can extract richer relational information. Finally, the decoder chooses the convolutional network ConvR. We conduct experiments on standard datasets such as FB15k-237 and WN18RR, and the experimental results confirm the effectiveness of the model, while also achieving relative improvements in Hits@N and MRR values compared to other classical models.