ABSTRACT
Although Few methods of deep learning have been proposed to deal with graphs that are dynamic in nature. Most of the existing recommendation systems based on social trust ignore the heterogeneous trust relationship between users and the heterogeneous interaction between users and products. And the appeal of a project can change over time, just as the dynamic interests of users are rarely considered, so is the relevance between projects. In order to overcome these limitations, a graph attention neural network Social recommendation (GNN-DR) model based on dynamic representation is proposed. Firstly, it considers the dynamic representation of users and items, and combines the influence of their relationship to model the short-term dynamic and long-term static interactive representation of item attractiveness. Second, the architecture systematically models user-user social diagrams and user-project diagrams, integrating heterogeneous trust and interactions. Finally, the attention mechanism is used to learn the potential factors of users and projects. Experiments on two real recommendation system datasets verify the validity of GNN-DR.
- W. Zhao, H. Ma, Z. Li, X. Ao, and N. Li, “Improving social and behavior recommendations via network embedding,” Information Sciences, vol.516, pp. 125–141, 2020.Google ScholarDigital Library
- W. Fan, Q. Li, and M. Cheng, “Deep modeling of social relations for recommendation,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1, 2018.Google ScholarCross Ref
- S. Deng, L. Huang, G. Xu, X. Wu, and Z. Wu, “On deep learning for trust-aware recommendations in social networks,” IEEE transactions on neural networks and learning systems, vol. 28, no. 5, pp. 1164–1177,2016.Google Scholar
- B. Yang, Y . Lei, J. Liu, and W. Li, “Social collaborative filtering by trust,” IEEE transactions on pattern analysis and machine intelligence,vol. 39, no. 8, pp. 1633–1647, 2016Google ScholarDigital Library
- Ruslan Salakhutdinov and Andriy Mnih. 2007. Probabilistic Matrix Factorization.In 21th Conference on Neural Information Processing Systems, Vol. 1. 2–1.Google Scholar
- Jiliang Tang, Xia Hu, Huiji Gao, and Huan Liu. 2013. Exploiting local and global social context for recommendation.. In IJCAI, Vol. 13. 2712–2718Google Scholar
- Rendle, S., Freudenthaler, C., Gantner, Z., & Schmidt-Thieme, L. (2012). BPR: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618.Google Scholar
- Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 855–864.Google ScholarDigital Library
- A Semantic VSM-Based Recommender System," International Journal of Computer Theory and Engineering vol. 5, no. 2, pp. 331-336, 2013Google Scholar
- A Prototype of a Recommended Nutrition and Energy Expenditure Application for Smartphones," International Journal of Computer Theory and Engineering vol. 8, no. 2, pp. 109-115, 2016.Google ScholarCross Ref
- A Personalized Product Based RecommendationnSystem Using Web Usage Mining and Semantic Web," International Journal of Computer Theory and Engineering vol. 4, no. 2, pp. 202-205, 2012.Google Scholar
- Bo Yang, Yu Lei, Jiming Liu, and Wenjie Li. 2017. Social collaborative filtering by trust. IEEE transactions on pattern analysis and machine intelligence 39, 8 (2017),1633–1647Google ScholarDigital Library
- Federico Monti, Michael Bronstein, and Xavier Bresson. 2017. Geometric matrix completion with recurrent multi-graph neural networks. In Advances in Neural Information Processing Systems. 3700–3710.Google Scholar
- Yang B, Lei Y, Liu J, Social collaborative filtering by trust[J]. IEEE transactions on pattern analysis and machine intelligence, 2016, 39(8): 1633-1647.Google Scholar
- Wu, Le, "Diffnet++: A neural influence and interest diffusion network for social recommendation." IEEE Transactions on Knowledge and Data Engineering 34.10 (2020): 4753-4766.Google Scholar
- Wu, Qitian, "Dual graph attention networks for deep latent representation of multifaceted social effects in recommender systems." The world wide web conference. 2019.Google Scholar
- Song, Weiping, "Session-based social recommendation via dynamic graph attention networks." Proceedings of the Twelfth ACM international conference on web search and data mining. 2019.Google Scholar
Index Terms
- Graph attention neural network social recommendation based on dynamic representation
Recommendations
A survey of graph neural network based recommendation in social networks
AbstractWith the widespread popularization of social network platforms, user-generated content and other social network data are growing rapidly. It is difficult for social users to select interested contents from the numerous social data. To ...
Federated Social Recommendation with Graph Neural Network
Recommender systems have become prosperous nowadays, designed to predict users’ potential interests in items by learning embeddings. Recent developments of the Graph Neural Networks (GNNs) also provide recommender systems (RSs) with powerful backbones to ...
Graph Neural Networks with Dynamic and Static Representations for Social Recommendation
Database Systems for Advanced ApplicationsAbstractRecommender systems based on graph neural networks receive increasing research interest due to their excellent ability to learn a variety of side information including social networks. However, previous works usually focus on modeling users, not ...
Comments