SocialTrans: A Deep Sequential Model with Social Information for Web-Scale Recommendation Systems
This addresses the challenge of improving recommendation accuracy on social networks by leveraging both user interests and friend influences, though it is incremental as it builds on existing deep learning and social recommendation techniques.
The authors tackled the problem of integrating personal and social preferences in web-scale recommendation systems by proposing SocialTrans, a deep sequential model that combines a Transformer for personal preference and a graph attention network for social influence, which they deployed in a major Chinese article recommendation system and showed outperforms state-of-the-art methods on three datasets.
On social network platforms, a user's behavior is based on his/her personal interests, or influenced by his/her friends. In the literature, it is common to model either users' personal preference or their socially influenced preference. In this paper, we present a novel deep learning model SocialTrans for social recommendations to integrate these two types of preferences. SocialTrans is composed of three modules. The first module is based on a multi-layer Transformer to model users' personal preference. The second module is a multi-layer graph attention neural network (GAT), which is used to model the social influence strengths between friends in social networks. The last module merges users' personal preference and socially influenced preference to produce recommendations. Our model can efficiently fit large-scale data and we deployed SocialTrans to a major article recommendation system in China. Experiments on three data sets verify the effectiveness of our model and show that it outperforms state-of-the-art social recommendation methods.