This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Heterogeneous Graph Structure Learning for Next Point-of-Interest Recommendation
by
Juan Chen
Juan Chen
Prof. Dr. Juan Chen obtained her Bachelor’s degree in Thermal Engineering from Shanghai University [...]
Prof. Dr. Juan Chen obtained her Bachelor’s degree in Thermal Engineering from Shanghai University of Technology (formerly East China University of Technology) in 1996, her Master’s degree in Control Theory and Control Engineering from Xi’an Jiaotong University in 2001, and her PhD degree in Control Theory and Control Engineering from Tongji University in 2008. From 1996 to 1998 and 2001 to 2003, she worked at the School of Electronic Information and Engineering, Northern University for Nationalities. Since 2009, she has been working at Sydney Business School, Shanghai University. Her main research areas are data mining, deep learning, reinforcement learning, and their applications in intelligent transportation systems, agriculture, commerce, and other fields.
1,2,*
and
Qiao Li
Qiao Li 1,*
1
SILC Business School, Shanghai University, Shanghai 201800, China
2
Smart City Research Institute, Shanghai University, Shanghai 201899, China
*
Authors to whom correspondence should be addressed.
Algorithms 2025, 18(8), 478; https://doi.org/10.3390/a18080478 (registering DOI)
Submission received: 7 June 2025
/
Revised: 24 July 2025
/
Accepted: 31 July 2025
/
Published: 3 August 2025
Abstract
Next Point-of-Interest (POI) recommendation is aimed at predicting users’ future visits based on their current status and historical check-in records, providing convenience to users and potential profits to businesses. The Graph Neural Network (GNN) has become a common approach for this task due to the capabilities of modeling relations between nodes in a global perspective. However, most existing studies overlook the more prevalent heterogeneous relations in real-world scenarios, and manually constructed graphs may suffer from inaccuracies. To address these limitations, we propose a model called Heterogeneous Graph Structure Learning for Next POI Recommendation (HGSL-POI), which integrates three key components: heterogeneous graph contrastive learning, graph structure learning, and sequence modeling. The model first employs meta-path-based subgraphs and the user–POI interaction graph to obtain initial representations of users and POIs. Based on these representations, it reconstructs the subgraphs through graph structure learning. Finally, based on the embeddings from the reconstructed graphs, sequence modeling incorporating graph neural networks captures users’ sequential preferences to make recommendations. Experimental results on real-world datasets demonstrate the effectiveness of the proposed model. Additional studies confirm its robustness and superior performance across diverse recommendation tasks.
Share and Cite
MDPI and ACS Style
Chen, J.; Li, Q.
Heterogeneous Graph Structure Learning for Next Point-of-Interest Recommendation. Algorithms 2025, 18, 478.
https://doi.org/10.3390/a18080478
AMA Style
Chen J, Li Q.
Heterogeneous Graph Structure Learning for Next Point-of-Interest Recommendation. Algorithms. 2025; 18(8):478.
https://doi.org/10.3390/a18080478
Chicago/Turabian Style
Chen, Juan, and Qiao Li.
2025. "Heterogeneous Graph Structure Learning for Next Point-of-Interest Recommendation" Algorithms 18, no. 8: 478.
https://doi.org/10.3390/a18080478
APA Style
Chen, J., & Li, Q.
(2025). Heterogeneous Graph Structure Learning for Next Point-of-Interest Recommendation. Algorithms, 18(8), 478.
https://doi.org/10.3390/a18080478
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.