Hierarchical Neighbor Propagation With Bidirectional Graph Attention Network for Relation Prediction

作者：Xie, Zhiwen; Zhu, Runjie; Liu, Jin^*; Zhou, Guangyou^*; Huang, Jimmy Xiangji

来源：IEEE-ACM Transactions on Audio Speech and Language Processing, 2021, 29: 1762-1773.

DOI：10.1109/TASLP.2021.3079812

• Natural language processing
• text mining
• knowledge graph
• representation learning

The graph attention network (GAT) [1] has started to become a mainstream neural network architecture since 2018, yielding remarkable performance gains in various natural language processing (NLP) tasks. Although GAT has reached the state-of-the-art (SOTA) performance as a recent success in relation prediction in know ledge graph, the current model is still limited by the following two aspects: (1) the existing model only considers the neighbors from the inbound-direction of the given entity, but ignores the rich neighborhood information from outbound-directions; (2) the existing model only uses the k-th hop output to learn the multi-hop embeddings, which leads to the loss of a large amount of early-stage embedding information (e.g., one-hop) at the graph attention step. In this study, we propose a novel bidirectional graph attention network (BiCAT) to learn the hierarchical neighbor propagation. In our proposed BiGAT, an inbound-directional GAT and an outbound-directional GAT are introduced to capture sufficient neighborhood information before propagating the bidirectional neighborhood information to learn the multi-hop feature embeddings in a hierarchical manner. Experiments conducted on the four publicly available datasets show that BiGAT achieves the competitive results in comparison to other SOTA methods.

• 单位
  1; 武汉大学