Diff-DGMN: A Diffusion-Based Dual Graph Multiattention Network for POI Recommendation
- 20 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (23) , 38393-38409
Abstract
Effective Point-of-Interest (POI) recommendation systems play a pivotal role in modern location-aware applications and human mobility, facilitating customized suggestions for users’ upcoming exploration destinations. Understanding the intricate dynamics of user movement, which are often influenced by a multitude of factors, remains a formidable task. Moreover, discrepancies between the acquired representation distribution and the authentic target distribution of user interests also present a notable obstacle. To tackle these problems, we make an attempt to bridge the gap by introducing diffusion models and propose a Diffusion-based Dual Graph Multi-attention Network (Diff-DGMN). Specifically, we have constructed two types of graphs: one is a user-oriented local POI transition graph, and the other is a global-based POI distance graph. Subsequently, we put forward two graph learning representation modules to capture the sequential encoding of users and the geographic representations of nodes, respectively. Furthermore, an attention-based location prototype generation module is introduced to merge the captured sequential encoding and geographic representation, yielding richer semantic interaction features. In the end, we obtain the final results by leveraging the forward diffusion process and corresponding its reverse-time generation to sample users’ future preferences from the posterior distribution. Our Diff-DGMN model demonstrates its remarkable recommendation performance through extensive experimentation on five real-world datasets. Compared with the most state-of-the-art methodologies, Diff-DGMN has improved performance in accuracy, normalized discounted cumulative gain (NDCG), and mean reciprocal rank (MRR) by 8.04%, 8.63%, and 9.09%, respectively. Our codes are available at https://github.com/JKZuo/Diff-DGMN.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB4501704)
- National Natural Science Foundation of China (72342026)
- Fundamental Research Funds for the Central Universities (2024-6-ZD-02)
This publication has 38 references indexed in Scilit:
- PG² Net: Personalized and Group Preferences Guided Network for Next Place PredictionIEEE Transactions on Intelligent Transportation Systems, 2024
- Contrastive graph learning long and short-term interests for POI recommendationExpert Systems with Applications, 2023
- Diffusion Models in Vision: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
- Kernel-based Substructure Exploration for Next POI Recommendation2022
- Deep-Distributed-Learning-Based POI Recommendation Under Mobile-Edge NetworksIEEE Internet of Things Journal, 2022
- Efficient Point-of-Interest Recommendation Services With Heterogenous Hypergraph EmbeddingIEEE Transactions on Services Computing, 2022
- Conversation-Based Adaptive Relational Translation Method for Next POI Recommendation With Uncertain Check-InsIEEE Transactions on Neural Networks and Learning Systems, 2022
- Where to Go Next: A Spatio-Temporal Gated Network for Next POI RecommendationIEEE Transactions on Knowledge and Data Engineering, 2020
- Personalized Long- and Short-term Preference Learning for Next POI RecommendationIEEE Transactions on Knowledge and Data Engineering, 2020
- Identity Mappings in Deep Residual Networks2016