Multipath-guided heterogeneous graph neural networks for sequential recommendation
Preprint
- 19 May 2023
- preprint
- Published by Springer Nature in Research Square
Abstract
With the explosion of information and users’ changing interest, program sequential recommendation becomes increasingly important for TV program platforms to help their users find interesting programs. Existing sequential recommendation methods mainly focus on modeling user preferences from users’ historical interaction behaviors directly, with insufficient learning about the dynamics of programs and users, while ignoring the rich semantic information from the heterogeneous graph. To address these issues, we propose the multipath-guided heterogeneous graph neural networks for TV program sequential recommendation (MHG-PSR), which can enhance the representations of programs and users through multiple paths in heterogeneous graphs. In our method, the auxiliary information is fused to supplement the semantics of program and user to obtain initial representations. Then, we explore the interactive behaviors of programs and users with temporal and auxiliary information to model the collaborative signals in the heterogeneous graph and extract the users’ dynamic preferences of programs. Extensive experiments on real-world datasets verify the proposed method can effectively improve the performance of TV program sequential recommendation.Keywords
All Related Versions
- Version 1, 2023-05-19, Research Square
- Published version: Computer Speech & Language, 87.
This publication has 10 references indexed in Scilit:
- Graph Neural Networks in Recommender Systems: A SurveyACM Computing Surveys, 2022
- Dynamic Graph Neural Networks for Sequential RecommendationIEEE Transactions on Knowledge and Data Engineering, 2022
- Enhanced graph recommendation with heterogeneous auxiliary informationComplex & Intelligent Systems, 2022
- Graph-based Embedding Smoothing for Sequential RecommendationIEEE Transactions on Knowledge and Data Engineering, 2021
- Personalized Graph Neural Networks With Attention Mechanism for Session-Aware RecommendationIEEE Transactions on Knowledge and Data Engineering, 2020
- On Both Cold-Start and Long-Tail Recommendation with Social DataIEEE Transactions on Knowledge and Data Engineering, 2019
- Heterogeneous Information Network Embedding for RecommendationIEEE Transactions on Knowledge and Data Engineering, 2018
- NAIS: Neural Attentive Item Similarity Model for RecommendationIEEE Transactions on Knowledge and Data Engineering, 2018
- Inferring Implicit Rules by Learning Explicit and Hidden Item DependencyIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2017
- FabCommunications of the ACM, 1997