文献类型：期刊文献

英文题名：SR-HGN: Semantic- and Relation-Aware Heterogeneous Graph Neural Network

作者：Wang, Zehong[1,2];Yu, Donghua[1];Li, Qi[1];Shen, Shigen[3];Yao, Shuang[4]

机构：[1]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[2]Univ Leeds, Sch Math, Leeds LS2 9JT, England;[3]Huzhou Univ, Sch Informat Engn, Huzhou 313000, Peoples R China;[4]China Jiliang Univ, Coll Econ & Management, Hangzhou 310018, Peoples R China

年份：2023

卷号：224

外文期刊名：EXPERT SYSTEMS WITH APPLICATIONS

收录：SCI-EXPANDED(收录号：WOS:000967063200001)、、EI(收录号：20231413841922)、Scopus(收录号：2-s2.0-85151358706)、WOS

基金：Acknowledgments This work was supported in part by the National Natural Science Foundation of China (No. 62002227, No. 62002226) , Fundamental Research Funds for the Provincial Universities of Zhejiang, China (No. 2021YW57) , Major Humanities and Social Sciences Research Projects in Zhejiang higher education institutions, China (No. 2023QN120) , and the Zhejiang Natural Science Foundation of China (No. LY22F020003, No. LZ22F020002) .

语种：英文

外文关键词：Graph neural network; Graph representation learning; Heterogeneous information network; Semantic-aware; Relation-aware

外文摘要：Graph Neural Networks (GNNs) have received considerable attention in recent years due to their unique ability to model both topologies and semantics in the graphs. In this paper, we explore the use of GNNs in learning low-dimensional node representations in Heterogeneous Information Networks (HINs), which retain rich semantic information across multiple types of nodes and relations. Existing methods for HINs generally focus on modeling heterogeneity at either the node level or the relation level, but not both. As a result, these methods often fall short of optimal performance. To address this issue, we propose a novel Semantic -and Relation-aware Heterogeneous Graph neural Network, dubbed SR-HGN, which jointly incorporates rich semantics preserved on nodes and relations. Our approach involves projecting the HINs into a low-dimensional vector space through two steps: node-level aggregation and type-level aggregation. The node-level aggregation employs an attention mechanism to create relation vectors by aggregating messages from neighborhoods connected via the same type of relation. The type-level aggregation leverages relation vectors to aggregate node representations. In particular, we introduce semantic-aware attention and relation-aware attention in the type-level aggregation to model the contributions of relation vectors, in order to simultaneously gain knowledge from node semantics and relational information. Unlike other approaches that rely on pre-defined meta-paths, our model can be readily applied to most real-world applications without requiring any domain knowledge. To validate the effectiveness of our proposed approach, we conducted extensive experiments on three public datasets. Experimental results demonstrate that the SR-HGN significantly outperforms state-of-the-art baselines on node classification and node clustering tasks.