Multi-relational graph attention networks for knowledge graph completion

Knowledge graphs are multi-relational data that contain massive entities and relations. As an effective graph representation technique based on deep learning, graph neural network has reported outstand-ing performance for modeling knowledge graphs in recent studies. However, previous graph neural network-based models have not fully considered the heterogeneity of knowledge graphs. Furthermore, the attention mechanism has demonstrated its great potential in many areas. In this paper, a novel heterogeneous graph neural network framework based on a hierarchical attention mechanism is proposed, including entity-level, relation-level, and self-level attentions. Thus, the proposed model can selectively aggregate informative features and weights them adequately. Then the learned embeddings of entities and relations can be utilized for the downstream tasks. Extensive experimental results on various heterogeneous graph tasks demonstrate the superior performance of the proposed model compared to several state-of-the-art methods. (C) 2022 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a novel heterogeneous graph neural network framework based on a hierarchical attention mechanism for modeling knowledge graphs. The proposed model achieves outstanding performance on various heterogeneous graph tasks.