Graph Attention Networks With Local Structure Awareness for Knowledge Graph Completion

作     者：Ji, Kexi Hui, Bei Luo, Guangchun 

作者机构：Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu 610054 Peoples R China Trusted Cloud Comp & Big Data Key Lab Sichuan Pro Chengdu 610054 Peoples R China 

出 版 物：《IEEE ACCESS》 (IEEE Access)

年 卷 期：2020年第8卷

页      面：224860-224870页

核心收录：

基　　金：National Key Research and Development Program of China [2018YFC0807500] National Natural Science Foundation of China [U19A2059] Ministry of Science and Technology of Sichuan Province Program [2018GZDZX0048, 20ZDYF0343] 

主　　题：Knowledge graph embedding knowledge graph completion graph attention networks 

摘      要：Graph neural networks have been proven to be very effective for representation learning of knowledge graphs. Recent methods such as SACN and CompGCN, have achieved the most advanced results in knowledge graph completion. However, previous efforts mostly rely on localized first-order approximations of spectral graph convolutions or first-order neighborhoods, ignoring the abundant local structures like cycles and stars. Therefore, the diverse semantic information beneath these structures is not well-captured, leaving opportunities for better knowledge representation which will finally help KGC. In this work, we propose LSA-GAT, a graph attention network with a novel neighborhood aggregation strategy for knowledge graph completion. The model can take special local structures into account, and derive a sophisticated representation covering both the semantic and structural information. Moreover, the LSA-GAT model is combined with a CNN-based decoder to form an encoder-decoder framework with a carefully designed training process. The experimental results show significant improvement of the proposed LSA-GAT compared to current state-of-the-art methods on FB15k-237 and WN18RR datasets.