With the increasing popularity of social network services, social network platforms provide rich and additional information for recommendation algorithms. More and more researchers utilize trust relationships of users to improve the performance of recommendation algorithms. However, most of existing social-network-based recommendation algorithms ignore the following problems: (1) In different domains, users tend to trust different friends. (2) the performance of recommendation algorithms is limited by the coarse-grained trust relationships. In this paper, we propose a novel recommendation algorithm that integrates social circles and network representation learning for item recommendation. Specifically, we first infer domain-specific social trust circles based on original users’ rating information and social network information. Next, we adopt network representation technique to embed domain-specific social trust circle into a low-dimensional space, and then utilize the low-dimensional representations of users to infer the fine-grained trust relationships between users. Finally, we integrate the fine-gained trust relationships into domain-specific matrix factorization model to learn latent user and item feature vectors. Experimental results on real-world datasets show that our proposed approach outperforms traditional social-network-based recommendation algorithms.
|Number of pages||8|
|Publication status||Published - 14 Jul 2019|
|Event||2019 International Joint Conference on Neural Networks - InterContinental Budapest Hotel, Budapest, Hungary|
Duration: 14 Jul 2019 → 19 Jul 2019
|Conference||2019 International Joint Conference on Neural Networks|
|Abbreviated title||IJCNN 2019|
|Period||14/07/19 → 19/07/19|