MGNN: Mutualistic Graph Neural Network for Joint Friend and Item Recommendation

Many social studies and practical cases suggest that people's consumption behaviors and social behaviors are not isolated but interrelated in social network services. However, most existing research either predicts users’ consumption preferences or recommends friends to users without dealing wi...

Full description

Saved in:
Bibliographic Details
Published in:IEEE intelligent systems 2020-09, Vol.35 (5), p.7-17
Main Authors: Xiao, Yang, Yao, Lina, Pei, Qingqi, Wang, Xianzhi, Yang, Jian, Sheng, Quan Z.
Format: Article
Language:English
Subjects:
Aggregates
Biological system modeling
Consumption
Feature extraction
Graph Neural Networks
Joint Recommendation
Mathematical model
Mutualistic Model
Neural networks
Predictive models
Social networking (online)
Social Networks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Many social studies and practical cases suggest that people's consumption behaviors and social behaviors are not isolated but interrelated in social network services. However, most existing research either predicts users’ consumption preferences or recommends friends to users without dealing with them simultaneously. We propose a holistic approach to predict users’ preferences on friends and items jointly and thereby make better recommendations. To this end, we design a graph neural network that incorporates a mutualistic mechanism to model the mutual reinforcement relationship between users’ consumption behaviors and social behaviors. Our experiments on the two-real world datasets demonstrate the effectiveness of our approach in both social recommendation and link prediction.
ISSN:1541-1672
1941-1294
DOI:10.1109/MIS.2020.2988925