期刊
NEURAL NETWORKS
卷 154, 期 -, 页码 234-245出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2022.07.014
关键词
Knowledge graph; Graph neural network; Attention mechanism
资金
- Postgraduate Innovation Development Fund Project of Shenzhen University, China [0000470814]
- National Natural Science Foundation of China [61976141, 61732011, 62106148]
- China Postdoctoral Science Foundation [2021M702259]
This article introduces a new multi-relational graph attention network (MRGAT) that can calculate the importance of different neighboring nodes in a knowledge graph, effectively improving the performance of the network.
One of the most effective ways to solve the problem of knowledge graph completion is embedding-based models. Graph neural networks (GNNs) are popular and promising embedding models which can exploit and use the structural information of neighbors in knowledge graphs. The current GNN-based knowledge graph completion methods assume that all neighbors of a node have equal importance. This assumption which cannot assign different weights to neighbors is pointed out in our study to be unreasonable. In addition, since the knowledge graph is a kind of heterogeneous graph with multiple relations, multiple complex interactions between nodes and neighbors can bring challenges to the effective message passing of GNNs. We then design a multi-relational graph attention network (MRGAT) which can adapt to different cases of heterogeneous multi-relational connections and then calculate the importance of different neighboring nodes through a self-attention layer. The incorporation of self-attention mechanism into the network with different node weights optimizes the network structure, and therefore, significantly results in a promotion of performance. We experimentally validate the rationality of our models on multiple benchmark knowledge graphs, where MRGAT achieves the best performance on various evaluation metrics including MRR score, Hits@ score compared with other state-of-the-art baseline models. (C) 2022 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据