Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading

With the explosive growth of information on the internet, personalized recommendation technology has become an important tool for helping users efficiently acquire information. However, existing spreading-based recommendation algorithms only consider user choices and fail to fully leverage the poten...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaowei Duan, Liang Zhang, Xu Lu, Junqing Li
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/4/1898
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722449186258944
author Yaowei Duan
Liang Zhang
Xu Lu
Junqing Li
author_facet Yaowei Duan
Liang Zhang
Xu Lu
Junqing Li
author_sort Yaowei Duan
collection DOAJ
description With the explosive growth of information on the internet, personalized recommendation technology has become an important tool for helping users efficiently acquire information. However, existing spreading-based recommendation algorithms only consider user choices and fail to fully leverage the potential relationships between users and items. Additionally, the incomplete utilization of user and item information limits their application potential and applicable scenarios, resulting in suboptimal recommendation performance in practical applications. To address this issue, we propose a Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading (LGCNHS). This algorithm first optimizes the embeddings of users and items using their respective feature matrix, then learns the latent embedding representations of users and items through a lightweight graph convolutional network. Finally, the latent embedding representations are incorporated as key parameters into the hybrid spreading recommendation algorithm to generate recommendations. Comparative experiments on two publicly available datasets, MovieLens and Douban, demonstrate that LGCNHS achieves improved accuracy and diversity in recommendations compared to related methods. The algorithm code is available on github.
format Article
id doaj-art-336b1cdd80d04577b43788fd3523a598
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-336b1cdd80d04577b43788fd3523a5982025-08-20T03:11:20ZengMDPI AGApplied Sciences2076-34172025-02-01154189810.3390/app15041898Light Graph Convolutional Recommendation Algorithm Based on Hybrid SpreadingYaowei Duan0Liang Zhang1Xu Lu2Junqing Li3College of Information Science and Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Taian 271018, ChinaWith the explosive growth of information on the internet, personalized recommendation technology has become an important tool for helping users efficiently acquire information. However, existing spreading-based recommendation algorithms only consider user choices and fail to fully leverage the potential relationships between users and items. Additionally, the incomplete utilization of user and item information limits their application potential and applicable scenarios, resulting in suboptimal recommendation performance in practical applications. To address this issue, we propose a Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading (LGCNHS). This algorithm first optimizes the embeddings of users and items using their respective feature matrix, then learns the latent embedding representations of users and items through a lightweight graph convolutional network. Finally, the latent embedding representations are incorporated as key parameters into the hybrid spreading recommendation algorithm to generate recommendations. Comparative experiments on two publicly available datasets, MovieLens and Douban, demonstrate that LGCNHS achieves improved accuracy and diversity in recommendations compared to related methods. The algorithm code is available on github.https://www.mdpi.com/2076-3417/15/4/1898recommendation systemspreading-based recommendationgraph convolutional network
spellingShingle Yaowei Duan
Liang Zhang
Xu Lu
Junqing Li
Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading
Applied Sciences
recommendation system
spreading-based recommendation
graph convolutional network
title Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading
title_full Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading
title_fullStr Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading
title_full_unstemmed Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading
title_short Light Graph Convolutional Recommendation Algorithm Based on Hybrid Spreading
title_sort light graph convolutional recommendation algorithm based on hybrid spreading
topic recommendation system
spreading-based recommendation
graph convolutional network
url https://www.mdpi.com/2076-3417/15/4/1898
work_keys_str_mv AT yaoweiduan lightgraphconvolutionalrecommendationalgorithmbasedonhybridspreading
AT liangzhang lightgraphconvolutionalrecommendationalgorithmbasedonhybridspreading
AT xulu lightgraphconvolutionalrecommendationalgorithmbasedonhybridspreading
AT junqingli lightgraphconvolutionalrecommendationalgorithmbasedonhybridspreading