Paper Recommendation with Multi-view Knowledge-Aware Attentive Network

The paper recommendation system aims to recommend potential papers of interest to users from massive data. Many efforts introduced knowledge graphs to solve problems such as data sparsity faced by traditional recommendation methods and used GNN-based techniques to mine the features of users and papers. However, existing work has not emphasized the quality of the knowledge graph construction, and has not optimized the modeling method from the scenario of paper recommendation, which makes the quality of recommendation results have room for improvement. In this paper, we proposed a Multi-View Knowledge-aware Attentive Network (MVKAN). Specifically, we first designed a knowledge graph construction method based on keynote extraction for better recommendation assistance. We then designed mechanisms for aggregation and propagation of graph attention from three views: the connectivity importance of entities, user’s time preferences, and short-cut links to users based on tag similarity. This helps to model the representation of users and papers more effectively. Results from the experiments show that our model outperforms the baselines.