SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering

With the flourishing of social media platforms, data in social networks, especially user-generated content, are growing rapidly, which makes it hard for users to select relevant content from the overloaded data. Recommender systems are thus developed to filter user-relevant content for better user e...

Ամբողջական նկարագրություն

Մատենագիտական մանրամասներ
Հիմնական հեղինակներ: Heng Lu, Ziwei Chen
Ձևաչափ: Հոդված
Լեզու:English
Հրապարակվել է: MDPI AG 2024-12-01
Շարք:Applied Sciences
Խորագրեր:
Առցանց հասանելիություն:https://www.mdpi.com/2076-3417/14/24/12070
_version_ 1826918141740974080
author Heng Lu
Ziwei Chen
author_facet Heng Lu
Ziwei Chen
author_sort Heng Lu
collection DOAJ
description With the flourishing of social media platforms, data in social networks, especially user-generated content, are growing rapidly, which makes it hard for users to select relevant content from the overloaded data. Recommender systems are thus developed to filter user-relevant content for better user experiences and also the commercial needs of social platform providers. Graph neural networks have been widely applied in recommender systems for better recommendation based on past interactions between users and corresponding items due to the graph structure of social data. Users might also be influenced by their social connections, which is the focus of social recommendation. Most works on recommendation systems try to obtain better representations of user embeddings and item embeddings. Compared with recommendation systems only focusing on interaction graphs, social recommendation has an additional task of combining user embedding from the social graph and interaction graph. This paper proposes a new method called SocialJGCF to address these problems, which applies Jacobi-Polynomial-Based Graph Collaborative Filtering (JGCF) to the propagation of the interaction graph and social graph, and a graph fusion is used to combine the user embeddings from the interaction graph and social graph. Experiments are conducted on two real-world datasets, epinions and LastFM. The result shows that SocialJGCF has great potential in social recommendation, especially for cold-start problems.
first_indexed 2025-02-17T12:45:28Z
format Article
id doaj.art-01d2cf26d6f7409c9bf26dbeb51dfdff
institution Directory Open Access Journal
issn 2076-3417
language English
last_indexed 2025-02-17T12:45:28Z
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj.art-01d2cf26d6f7409c9bf26dbeb51dfdff2024-12-27T14:09:18ZengMDPI AGApplied Sciences2076-34172024-12-0114241207010.3390/app142412070SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative FilteringHeng Lu0Ziwei Chen1Department of Computer Science, Metropolitan College, Boston University, Boston, MA 02215, USADepartment of Electronics, Beijing Jiaotong University, Beijing 100044, ChinaWith the flourishing of social media platforms, data in social networks, especially user-generated content, are growing rapidly, which makes it hard for users to select relevant content from the overloaded data. Recommender systems are thus developed to filter user-relevant content for better user experiences and also the commercial needs of social platform providers. Graph neural networks have been widely applied in recommender systems for better recommendation based on past interactions between users and corresponding items due to the graph structure of social data. Users might also be influenced by their social connections, which is the focus of social recommendation. Most works on recommendation systems try to obtain better representations of user embeddings and item embeddings. Compared with recommendation systems only focusing on interaction graphs, social recommendation has an additional task of combining user embedding from the social graph and interaction graph. This paper proposes a new method called SocialJGCF to address these problems, which applies Jacobi-Polynomial-Based Graph Collaborative Filtering (JGCF) to the propagation of the interaction graph and social graph, and a graph fusion is used to combine the user embeddings from the interaction graph and social graph. Experiments are conducted on two real-world datasets, epinions and LastFM. The result shows that SocialJGCF has great potential in social recommendation, especially for cold-start problems.https://www.mdpi.com/2076-3417/14/24/12070graph neural networksocial recommendationrecommender systemgraph collaborative filtering
spellingShingle Heng Lu
Ziwei Chen
SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering
Applied Sciences
graph neural network
social recommendation
recommender system
graph collaborative filtering
title SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering
title_full SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering
title_fullStr SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering
title_full_unstemmed SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering
title_short SocialJGCF: Social Recommendation with Jacobi Polynomial-Based Graph Collaborative Filtering
title_sort socialjgcf social recommendation with jacobi polynomial based graph collaborative filtering
topic graph neural network
social recommendation
recommender system
graph collaborative filtering
url https://www.mdpi.com/2076-3417/14/24/12070
work_keys_str_mv AT henglu socialjgcfsocialrecommendationwithjacobipolynomialbasedgraphcollaborativefiltering
AT ziweichen socialjgcfsocialrecommendationwithjacobipolynomialbasedgraphcollaborativefiltering