Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation

Personalized recommendation can recommend items of interest to different users and is widely used in the real world. Among them, graph collaborative filtering is a method of personalized recommendation. It can enrich the connection between users and items on the basis of collaborative filtering, to...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhe Liu, Xiaojun Lou, Jian Li, Guanjun Liu
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Applied Artificial Intelligence
Online Access:https://www.tandfonline.com/doi/10.1080/08839514.2024.2355425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850116201871572992
author Zhe Liu
Xiaojun Lou
Jian Li
Guanjun Liu
author_facet Zhe Liu
Xiaojun Lou
Jian Li
Guanjun Liu
author_sort Zhe Liu
collection DOAJ
description Personalized recommendation can recommend items of interest to different users and is widely used in the real world. Among them, graph collaborative filtering is a method of personalized recommendation. It can enrich the connection between users and items on the basis of collaborative filtering, to learn the embedded representation of nodes more accurately. Since graph collaborative filtering is based on bipartite graphs, few exciting graph collaborative methods consider the relationships between users (or items), the message between homogeneous nodes are diluted or ignored. Predicting and constructing the relationship between users (or items) has become a challenging. To solve this problem, we propose an enhanced sub-graph reconstruction graph neural network for recommendation (SRCF), using a heterogeneous graph neural network based encoder-decoder learn potential relationships between users (or items), and reconstruct sub-graphs based on those relationships. In the proposed model, the information of user and item sub-graphs is merged with the network of graph collaborative filtering, which enhances effective information transfer between homogeneous nodes, thereby improving the model performance. We have selected a number of data sets of different scenarios and different scales to comprehensively evaluate the performance of the model, and the experimental results confirmed the superiority of our model.
format Article
id doaj-art-6d5aa9ec9a334506b0d47182dcbbed98
institution OA Journals
issn 0883-9514
1087-6545
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Applied Artificial Intelligence
spelling doaj-art-6d5aa9ec9a334506b0d47182dcbbed982025-08-20T02:36:22ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452024-12-0138110.1080/08839514.2024.2355425Enhanced Sub-graph Reconstruction Graph Neural Network for RecommendationZhe Liu0Xiaojun Lou1Jian Li2Guanjun Liu3College of Media Engineering, Communication University of Zhejiang, Hangzhou, ChinaSchool of Mathematics and Computer science, Zhejiang A and F University, Hangzhou, ChinaSchool of Mathematics and Computer science, Zhejiang A and F University, Hangzhou, ChinaCollege of Electronic and Information Engineering, Tongji University, Shanghai, ChinaPersonalized recommendation can recommend items of interest to different users and is widely used in the real world. Among them, graph collaborative filtering is a method of personalized recommendation. It can enrich the connection between users and items on the basis of collaborative filtering, to learn the embedded representation of nodes more accurately. Since graph collaborative filtering is based on bipartite graphs, few exciting graph collaborative methods consider the relationships between users (or items), the message between homogeneous nodes are diluted or ignored. Predicting and constructing the relationship between users (or items) has become a challenging. To solve this problem, we propose an enhanced sub-graph reconstruction graph neural network for recommendation (SRCF), using a heterogeneous graph neural network based encoder-decoder learn potential relationships between users (or items), and reconstruct sub-graphs based on those relationships. In the proposed model, the information of user and item sub-graphs is merged with the network of graph collaborative filtering, which enhances effective information transfer between homogeneous nodes, thereby improving the model performance. We have selected a number of data sets of different scenarios and different scales to comprehensively evaluate the performance of the model, and the experimental results confirmed the superiority of our model.https://www.tandfonline.com/doi/10.1080/08839514.2024.2355425
spellingShingle Zhe Liu
Xiaojun Lou
Jian Li
Guanjun Liu
Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation
Applied Artificial Intelligence
title Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation
title_full Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation
title_fullStr Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation
title_full_unstemmed Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation
title_short Enhanced Sub-graph Reconstruction Graph Neural Network for Recommendation
title_sort enhanced sub graph reconstruction graph neural network for recommendation
url https://www.tandfonline.com/doi/10.1080/08839514.2024.2355425
work_keys_str_mv AT zheliu enhancedsubgraphreconstructiongraphneuralnetworkforrecommendation
AT xiaojunlou enhancedsubgraphreconstructiongraphneuralnetworkforrecommendation
AT jianli enhancedsubgraphreconstructiongraphneuralnetworkforrecommendation
AT guanjunliu enhancedsubgraphreconstructiongraphneuralnetworkforrecommendation