Hierarchical Neighbor Propagation With Bidirectional Graph Attention Network for Relation Prediction
Hierarchical Neighbor Propagation With Bidirectional Graph Attention Network for Relation Prediction
复制标题
DOI：
10.1109/taslp.2021.3079812
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Zhiwen Xie;Runjie Zhu;Jin Liu;Guangyou Zhou;J. Huang
中科院分区：
文献类型：
--
作者：
Zhiwen Xie;Runjie Zhu;Jin Liu;Guangyou Zhou;J. Huang
自2018年以来，图注意力网络（GAT）[1]已开始成为主流神经网络架构，在各种自然语言处理（NLP）任务中产生了显着的性能提升。虽然GAT在知识图的关系预测方面取得了很大的成功，达到了SOTA（state-of-the-art）的性能，但是现有的模型仍然受到以下两个方面的限制：（1）现有的模型只考虑了给定实体的入向邻居，而忽略了出向邻居的丰富信息;（2）现有模型仅使用第k跳输出来学习多跳嵌入，这导致大量早期嵌入信息（例如，一跳）。在这项研究中，我们提出了一种新的双向图注意力网络（BiGAT）来学习分层邻居传播。在我们提出的BiGAT中，引入了一个向内方向的GAT和一个向外方向的GAT来捕获足够的邻域信息，然后传播双向邻域信息，以分层的方式学习多跳特征嵌入。在四个公开数据集上进行的实验表明，与其他SOTA方法相比，BiGAT实现了具有竞争力的结果。
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 knowledge 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 (BiGAT) 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.