An integrated network embedding with reinforcement learning for explainable recommendation

Abstract

Within the explainable recommendation field, most of recent knowledge graphs (KG)-oriented recommendation techniques mainly focus on the direct interactions between entities in a given KG. These interactions are considered as the rich information sources for leveraging the quality of recommendation outputs. However, these recent recommendation techniques are still hindered by the heterogeneity, type-varied entities and their relationships in a given KG as the heterogeneous information networks (HIN). This limitation seems challenging to build up an effective approach for the KG-based recommendation system in both semantic path-based exploitation and heterogeneous information extraction. In order to overcome these challenges, we proposed a novel integrated HIN embedding with reinforcement learning (RL)-based feature engineering for recommendation, called as: HINRL4Rec. First of all, we apply the combined textual meta-path-based embedding approach for learning multiple-rich-schematic representations of user/item and their associated entities. Then, these extracted multi-typed embeddings of user and item entities are fused into the unified embedding spaces during the KG embedding process. In the end, the combined representations of users and items are used to facilitate the RL-based policy-driven searching process in the next steps for performing the explainable recommendation task. Extensive experiments in real-world datasets demonstrate the effectiveness of our proposed model in comparing with recent state-of-the-art recommendation baselines.