Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction

With the widespread adoption of mobile devices and the increasing availability of user trajectory data, accurately predicting the next location a user will visit has become a pivotal task in location-based services. Despite recent progress, existing methods often fail to effectively disentangle the...

Full description

Saved in:
Bibliographic Details
Main Authors: Fengyu Liu, Kexin Zhang, Chao Lian, Yunong Tian
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/14/7672
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849246419353862144
author Fengyu Liu
Kexin Zhang
Chao Lian
Yunong Tian
author_facet Fengyu Liu
Kexin Zhang
Chao Lian
Yunong Tian
author_sort Fengyu Liu
collection DOAJ
description With the widespread adoption of mobile devices and the increasing availability of user trajectory data, accurately predicting the next location a user will visit has become a pivotal task in location-based services. Despite recent progress, existing methods often fail to effectively disentangle the diverse and entangled behavioral signals, such as collaborative user preferences, global transition mobility patterns, and geographical influences, embedded in user trajectories. To address these challenges, we propose a novel framework named Multi-Perspective Hypergraphs with Contrastive Learning (MPHCL), which explicitly captures and disentangles user preferences from three complementary perspectives. Specifically, MPHCL constructs a global transition flow graph and two specialized hypergraphs: a collective preference hypergraph to model collaborative check-in behavior and a geospatial-context hypergraph to reflect geographical proximity relationships. A unified hypergraph representation learning network is developed to preserve semantic independence across views through a dual propagation mechanism. Furthermore, we introduce a cross-view contrastive learning strategy that aligns multi-perspective embeddings by maximizing agreement between corresponding user and location representations across views while enhancing discriminability through negative sampling. Extensive experiments conducted on two real-world datasets demonstrate that MPHCL consistently outperforms state-of-the-art baselines. These results validate the effectiveness of our multi-perspective learning paradigm for next-location prediction.
format Article
id doaj-art-aadfb6618cd74dbe89fbed73a3d09011
institution Kabale University
issn 2076-3417
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-aadfb6618cd74dbe89fbed73a3d090112025-08-20T03:58:30ZengMDPI AGApplied Sciences2076-34172025-07-011514767210.3390/app15147672Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location PredictionFengyu Liu0Kexin Zhang1Chao Lian2Yunong Tian3College of Information Technology, Shanghai Ocean University, Shanghai 201306, ChinaCollege of Information Technology, Shanghai Ocean University, Shanghai 201306, ChinaSchool of Information Science and Engineering, Northeastern University, Shenyang 110819, ChinaEngineering Laboratory of Industrial Vision Intelligent Equipment Technology, Chinese Academy of Sciences, Beijing 100190, ChinaWith the widespread adoption of mobile devices and the increasing availability of user trajectory data, accurately predicting the next location a user will visit has become a pivotal task in location-based services. Despite recent progress, existing methods often fail to effectively disentangle the diverse and entangled behavioral signals, such as collaborative user preferences, global transition mobility patterns, and geographical influences, embedded in user trajectories. To address these challenges, we propose a novel framework named Multi-Perspective Hypergraphs with Contrastive Learning (MPHCL), which explicitly captures and disentangles user preferences from three complementary perspectives. Specifically, MPHCL constructs a global transition flow graph and two specialized hypergraphs: a collective preference hypergraph to model collaborative check-in behavior and a geospatial-context hypergraph to reflect geographical proximity relationships. A unified hypergraph representation learning network is developed to preserve semantic independence across views through a dual propagation mechanism. Furthermore, we introduce a cross-view contrastive learning strategy that aligns multi-perspective embeddings by maximizing agreement between corresponding user and location representations across views while enhancing discriminability through negative sampling. Extensive experiments conducted on two real-world datasets demonstrate that MPHCL consistently outperforms state-of-the-art baselines. These results validate the effectiveness of our multi-perspective learning paradigm for next-location prediction.https://www.mdpi.com/2076-3417/15/14/7672location predictionhuman mobilitydisentangled representationhypergraph neural networkscontrastive learning
spellingShingle Fengyu Liu
Kexin Zhang
Chao Lian
Yunong Tian
Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction
Applied Sciences
location prediction
human mobility
disentangled representation
hypergraph neural networks
contrastive learning
title Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction
title_full Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction
title_fullStr Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction
title_full_unstemmed Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction
title_short Capturing User Preferences via Multi-Perspective Hypergraphs with Contrastive Learning for Next-Location Prediction
title_sort capturing user preferences via multi perspective hypergraphs with contrastive learning for next location prediction
topic location prediction
human mobility
disentangled representation
hypergraph neural networks
contrastive learning
url https://www.mdpi.com/2076-3417/15/14/7672
work_keys_str_mv AT fengyuliu capturinguserpreferencesviamultiperspectivehypergraphswithcontrastivelearningfornextlocationprediction
AT kexinzhang capturinguserpreferencesviamultiperspectivehypergraphswithcontrastivelearningfornextlocationprediction
AT chaolian capturinguserpreferencesviamultiperspectivehypergraphswithcontrastivelearningfornextlocationprediction
AT yunongtian capturinguserpreferencesviamultiperspectivehypergraphswithcontrastivelearningfornextlocationprediction