摘要
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.
学科与关键词
- Learning Knowledge Graph Embedding With Heterogeneous Relation Attention NetworksLi, Zhifei; Liu, Hai*; Zhang, Zhaoli; Liu, Tingting; Xiong, Neal N.IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(8): 3961-3973.被引 142
- Graph attention network with dynamic representation of relations for knowledge graph completionZhang, Xin; Zhang, Chunxia*; Guo, Jingtao; Peng, Cheng; Niu, Zhendong; Wu, XindongEXPERT SYSTEMS WITH APPLICATIONS, 2023, 219: 119616.被引 6
- Learning knowledge graph embedding with multi-granularity relational augmentation networkXue, Zengcan; Zhang, Zhaoli; Liu, Hai*; Yang, Shuoqiu; Han, ShuyunEXPERT SYSTEMS WITH APPLICATIONS, 2023, 233: 120953.被引 3
