Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks

In recent years, graph neural networks (GNNs) have been widely applied in recommendation systems. However, most existing GNN models do not fully consider the complex relationships between heterogeneous nodes and ignore the high-order semantic information in the interactions between different types o...

Full description

Saved in:
Bibliographic Details
Main Authors: Siyue Li, Tian Jin, Hao Luo, Erfan Wang, Ranting Tao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/9/1479
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850032170555408384
author Siyue Li
Tian Jin
Hao Luo
Erfan Wang
Ranting Tao
author_facet Siyue Li
Tian Jin
Hao Luo
Erfan Wang
Ranting Tao
author_sort Siyue Li
collection DOAJ
description In recent years, graph neural networks (GNNs) have been widely applied in recommendation systems. However, most existing GNN models do not fully consider the complex relationships between heterogeneous nodes and ignore the high-order semantic information in the interactions between different types of nodes, which limits the recommendation performance. To address these issues, this paper proposes a heterogeneous graph neural network recommendation model based on high-order semantics and node attention (HAS-HGNN). Firstly, HAS-HGNN aggregates the features of direct neighboring nodes through an interest aggregation layer to capture the information of items that users are interested in. This method of capturing the features of directly interacting nodes can effectively uncover users’ potential interests. Meanwhile, considering that users with multiple interactions may share similar interests, in the common interest feature capture layer, HAS-HGNN utilizes semantic relationships to capture the features of users with the same interests, generating common interest features among users with multiple interactions. Finally, HAS-HGNN combines the direct features of users with the interest features between other users through a feature fusion layer to generate the final feature representation. Experimental results show that the proposed model significantly outperforms existing baseline methods on multiple real-world datasets, providing new insights and methods for the application of heterogeneous graph neural networks in recommendation systems.
format Article
id doaj-art-2a7ff2bc912e47e5ac74e77f0aa55831
institution DOAJ
issn 2227-7390
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-2a7ff2bc912e47e5ac74e77f0aa558312025-08-20T02:58:44ZengMDPI AGMathematics2227-73902025-04-01139147910.3390/math13091479Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural NetworksSiyue Li0Tian Jin1Hao Luo2Erfan Wang3Ranting Tao4Khoury College of Computer Sciences, Northeastern University, Santa Clara, MA 02115, USACollege of Computing, Georgia Institute of Technology, Atlanta, GA 30332, USAComputer Science, Rutgers University, Fremont, CA 94536, USAGeorge R. Brown School of Engineering and Computing, Rice University, Houston, TX 77005, USAMeta Platform, Statistics, 243 Blaze Climber Way, Rockville, MD 20850, USAIn recent years, graph neural networks (GNNs) have been widely applied in recommendation systems. However, most existing GNN models do not fully consider the complex relationships between heterogeneous nodes and ignore the high-order semantic information in the interactions between different types of nodes, which limits the recommendation performance. To address these issues, this paper proposes a heterogeneous graph neural network recommendation model based on high-order semantics and node attention (HAS-HGNN). Firstly, HAS-HGNN aggregates the features of direct neighboring nodes through an interest aggregation layer to capture the information of items that users are interested in. This method of capturing the features of directly interacting nodes can effectively uncover users’ potential interests. Meanwhile, considering that users with multiple interactions may share similar interests, in the common interest feature capture layer, HAS-HGNN utilizes semantic relationships to capture the features of users with the same interests, generating common interest features among users with multiple interactions. Finally, HAS-HGNN combines the direct features of users with the interest features between other users through a feature fusion layer to generate the final feature representation. Experimental results show that the proposed model significantly outperforms existing baseline methods on multiple real-world datasets, providing new insights and methods for the application of heterogeneous graph neural networks in recommendation systems.https://www.mdpi.com/2227-7390/13/9/1479recommendation systemheterogeneous graph neural networkattention mechanism
spellingShingle Siyue Li
Tian Jin
Hao Luo
Erfan Wang
Ranting Tao
Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks
Mathematics
recommendation system
heterogeneous graph neural network
attention mechanism
title Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks
title_full Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks
title_fullStr Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks
title_full_unstemmed Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks
title_short Recommendation Model Based on Higher-Order Semantics and Node Attention in Heterogeneous Graph Neural Networks
title_sort recommendation model based on higher order semantics and node attention in heterogeneous graph neural networks
topic recommendation system
heterogeneous graph neural network
attention mechanism
url https://www.mdpi.com/2227-7390/13/9/1479
work_keys_str_mv AT siyueli recommendationmodelbasedonhigherordersemanticsandnodeattentioninheterogeneousgraphneuralnetworks
AT tianjin recommendationmodelbasedonhigherordersemanticsandnodeattentioninheterogeneousgraphneuralnetworks
AT haoluo recommendationmodelbasedonhigherordersemanticsandnodeattentioninheterogeneousgraphneuralnetworks
AT erfanwang recommendationmodelbasedonhigherordersemanticsandnodeattentioninheterogeneousgraphneuralnetworks
AT rantingtao recommendationmodelbasedonhigherordersemanticsandnodeattentioninheterogeneousgraphneuralnetworks