A Multi-hop Path Query Answering Model for Knowledge Graph based on Neighborhood Aggregation and Transformer

Abstract

Multi-hop path query answering is a complex task in which a path needs to be inferred from a knowledge graph that contains a head entity and multi-hop relations. The objective is to identify the corresponding tail entity accurately. The representation of the path is a critical factor in this task. However, existing methods do not adequately consider the context information of the entities and relations in the path. To address this issue, this paper proposes a novel multi-hop path query answering model that utilizes an enhanced reasoning path feature representation to incorporate intermediate entity information and improve the accuracy of path query answering. The proposed model utilizes the neighborhood to aggregate the entity representation in the reasoning path. It employs a recurrent skipping network to splice the embedding of the relationship and the entity in the reasoning path based on their weight. Additionally, the model adds the position representation to obtain the reasoning path representation. Moreover, the model uses Bi-GRU and Transformer to obtain the local and global context features of each entity in the reasoning path. Finally, the reasoning path feature representation is input into the feedforward neural network and predicted through the softmax layer. The effectiveness of the proposed model in addressing the multi-hop path query answering task is demonstrated by experimental results on the WN18RR and FB15K-237 datasets. Specifically, the proposed model outperforms existing methods in terms of accuracy.