Associate Professor Liu Shudong, a researcher at the base, participated in the collaborative paper titled "Social Recommendation Model Based on Self-Supervised Tri-Training and Consistent Neighbor Aggregation", which was published in the Important academic journal Pattern Recognition and Artificial Intelligence.

Pattern Recognition and Artificial Intelligence mainly publishes and reports research achievements and progress in pattern recognition, artificial intelligence, intelligent systems, and other fields, aiming to promote the development of information science and technology.

Abstact：Integrating user social relationships into user-item rating data to construct a heterogeneous user-item graph can alleviate data sparsity and cold start in traditional recommender systems. However, due to the complexity of user social relationships, aggregating inconsistent neighbors may degrade the recommendation performance. To address this issue, a social recommendation model based on self-supervised tri-training and consistent neighbor aggregation(SR-STCNA) is proposed. Firstly, on the basis of user-item rating data, social relationships among users are introduced and diverse relations within the heterogeneous user-item graph are established. The relationships between users as well as between users and items are presented by a hypergraph. Self-supervised tri-training is employed to learn users' representations from unlabeled data and uncover the complex connectivity between user-user and user-item interactions. Then, the consistent neighbors of users and items are aggregated in the process of their representation learning by the node consistency score and relationship self-attention on the user-item heterogeneous graph. Consequently, the representation ability of users and items is enhanced, thereby improving the recommendation performance. Finally, the experimental results on CiaoDVD, FilmTrust, Last.fm and Yelp datasets validate the superiority of SR-STCNA.

Keywords：Social Recommendation; Collaborative Filtering; Data Sparsity; Hypergraph; Consistent Neighbor

Link：http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202403002

Author profile

LIU Shudong, associate professor, master supervisor, and Wenlan Young Scholar, graduated from the School of Computer Science of Beijing University of Posts and Telecommunications with a Ph.D. in July 2015. His main research directions are data mining, machine learning, and recommendation systems. He has published more than 30 papers in domestic and international academic journals or conferences, and has hosted or participated in 3 projects of the National Natural Science Foundation of China, 1 project of the National Social Science Fund, and 6 projects of the basic scientific research fund of central universities.