Overcoming Data Sparsity in Group Recommendation

• Published in: IEEE transactions on knowledge and data engineering 2022-07, Vol.34 (7), p.3447-3460
• Main Authors: Yin, Hongzhi, Wang, Qinyong, Zheng, Kai, Li, Zhixu, Zhou, Xiaofang
• Format: Article
• Language: English
• Subjects: Agglomeration; Aggregates; Bipartite graph; Data models; data sparsity; Decision making; Graph theory; group recommendation; Learning; network embedding; Optimization; Preferences; Recommender system; Recommender systems; Representations; Social network services; Social networks; Sparsity; Task analysis
• ISSN: 1041-4347; 1558-2191
• DOI: 10.1109/TKDE.2020.3023787

It has been an important task for recommender systems to suggest satisfying activities to a group of users in people's daily social life. The major challenge in this task is how to aggregate personal preferences of group members to infer the decision of a group. Conventional group recommendation methods applied a predefined strategy for preference aggregation. However, these static strategies are too simple to model the real and complex process of group decision-making, especially for occasional groups which are formed ad-hoc. Moreover, group members should have non-uniform influences or weights in a group, and the weight of a user can be varied in different groups. Therefore, an ideal group recommender system should be able to accurately learn not only users' personal preferences but also the preference aggregation strategy from data. In this paper, we propose a novel end-to-end group recommender system named CAGR (short for " C entrality- A ware G roup R ecommender"), which takes Bipartite Graph Embedding Model (BGEM), the self-attention mechanism and Graph Convolutional Networks (GCNs) as basic building blocks to learn group and user representations in a unified way. Specifically, we first extend BGEM to model group-item interactions, and then in order to overcome the limitation and sparsity of the interaction data generated by occasional groups, we propose a self-attentive mechanism to represent groups based on the group members. In addition, to overcome the sparsity issue of user-item interaction data, we leverage the user social networks to enhance user representation learning, obtaining centrality-aware user representations. To further alleviate the group data sparsity problem, we propose two model optimization approaches to seamlessly integrate the user representations learning process. We create three large-scale benchmark datasets and conduct extensive experiments on them. The experimental results show the superiority of our proposed CAGR by comparing it with state-of-the-art group recommender models.