Abstract
Social information is usually jointly utilized with rating information to help the traditional recommendation system providing more personalized services, while how to make full use of social information to build better recommendation models still faces lots of challenges. In this paper, we propose a novel social recommendation model taking advantage of both deep and shallow model, with deep auto-encoders acting as the nonlinear feature extractor and MF-based method being used to depict the user's preferences. Then, motivated by the idea of word2vec, we provide an appealing method that embeds users into latent space and meanwhile preserves the structural information of social networks during the embedding. Also, the embedded latent features of each user are corresponding to the dual roles the user plays in the recommendation. Furthermore, we design a loss function for the holistic training of the model, and our loss function is made up mainly of three parts which embody the effects of different factors on the rating predictions. Specifically, the loss function (i) captures the personal preference from user-item adoption matrix based on matrix factorization, (ii) discriminates the two different social functions of users and further evaluates the effects of interpersonal influence through user embedding and social influence matrix, (iii) and avoids overfitting by imposing a quadratic regularization penalty. As a result, our model can predict the missing ratings with the MF-based method by consuming the latent features of users and items extracted by the deep model. The experiments show that our method outperforms existing methods and performs well on cold start users.
Highlights
As one of the most important infrastructures of solving information overload, the recommendation system is proved to be a powerful solution for retrieving valuable information and providing personalized business services
To fully mine and exploit the nonlinear feature of social data, maintain the structural information during embedding the users into latent feature space, and make the recommendation closer to reality, we propose a novel social recommendation model named as Neural Social Recommendation(NSR) taking advantages of both deep and shallow models
RELATED WORKS The social recommendation model aims to boost the performance of the traditional recommendation system assisted by additional social information, and how to integrate social data into the model is the most important part or the heart of this issue
Summary
As one of the most important infrastructures of solving information overload, the recommendation system is proved to be a powerful solution for retrieving valuable information and providing personalized business services. To fully mine and exploit the nonlinear feature of social data, maintain the structural information during embedding the users into latent feature space, and make the recommendation closer to reality, we propose a novel social recommendation model named as Neural Social Recommendation(NSR) taking advantages of both deep and shallow models. The feature extraction block is implemented by the deep model with deep auto-encoders embedding the users and items into the latent feature space, and the rating prediction block is constructed by the shallow model with the MF-based method being used to fit the rating data. The contributions of our works are summarized as: We propose a novel NSR model which takes advantage of both deep and shallow models by extracting latent features of users and items via deep auto-encoder and linearly modeling user’s preferences via the MF-based. The structure of the rest of this paper is organized as follows: the related research works are reviewed in section II, we explain the detailed procedure of formulating NSR model in section III, after that we present the experimental results in section IV, and draw our conclusions in the last section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
