Entity Recommendation With Negative Feedback Memory Networks for Topic-Oriented Knowledge Graph Exploration

Knowledge graph exploration is an interactive knowledge discovery process over the knowledge graph. Entity recommendation deals with the information overflow issue when exploring the large-scale unfamiliar knowledge graphs. The traditional personalized entity recommendation methods for knowledge graph explorations rarely consider the adaptive topic-oriented long-term positive- and negative intent modeling. In this article, we propose a topic-oriented entity recommendation method during the knowledge graph exploration. We build a negative feedback memory network model for obtaining the user's long-term negative intents. We propose a transformer-based sequence encoder for the positive intents. We dynamically obtain the adaptive intents by aggregating the positive- and negative intents by the proposed intent attention mechanism. Experiments show that our method has advantages in TopK entity recommendations.