Friend Link Prediction Method Based on Heterogeneous Multigraph and Hierarchical Attention

With the rapid growth of location-based social network (LBSN), rich data comprising social behaviors and location information among users has emerged. Predicting potential friendships accurately from abundant information has become a pivotal research area. While graph neural network (GNN) have shown...

Full description

Saved in:
Bibliographic Details
Main Authors: Aoxue Liu, Boyu Li, Yong Wang, Ziteng Yang
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Applied Artificial Intelligence
Online Access:https://www.tandfonline.com/doi/10.1080/08839514.2024.2427545
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the rapid growth of location-based social network (LBSN), rich data comprising social behaviors and location information among users has emerged. Predicting potential friendships accurately from abundant information has become a pivotal research area. While graph neural network (GNN) have shown significant promise in prediction, existing approaches often fail to fully exploit the heterogeneous data characteristics in LBSN. Key challenges include inadequate modeling of the intricate relationships between users and points of interest (POI), overlooking the significance of spatial-temporal information in user trajectories, and underutilizing rich edge features. To address these challenges, we design a novel GRU-enhanced Heterogeneous Multigraph Attention Network (GEHMAN), which is a GNN model enhanced by GRU. We construct a heterogeneous multigraph to comprehensively capture user-POI relationships. We then employ a skip-gram model to embed POI nodes from user sub-trajectories and use RNN with GRU units to embed user nodes. GEHMAN utilize hierarchical attention mechanism to consolidate node information by aggregating diverse types of neighboring nodes and connecting edges. Experiments on six real city datasets show that compared with the best performance of six benchmark methods including LBSN2vec++, Metapath2vec and HAN, the average improvement percentages of GEHMAN in AUC, AP, and Top@K are 2.225%, 1.948%, and 6.353%, respectively.
ISSN:0883-9514
1087-6545