Abstract

To facilitate more accurate and explainable recommendation, it is crucial to incorporate side information into user-item interactions. Recently, knowledge graph (KG) has attracted much attention in a variety of domains due to its fruitful facts and abundant relations. However, the expanding scale of real-world data graphs poses severe challenges. In general, most existing KG-based algorithms adopt exhaustively hop-by-hop enumeration strategy to search all the possible relational paths, this manner involves extremely high-cost computations and is not scalable with the increase of hop numbers. To overcome these difficulties, in this article, we propose an end-to-end framework Knowledge-tree-routed UseR-Interest Trajectories Network (KURIT-Net). KURIT-Net employs the user-interest Markov trees (UIMTs) to reconfigure a recommendation-based KG, striking a good balance for routing knowledge between short-distance and long-distance relations between entities. Each tree starts from the preferred items for a user and routes the association reasoning paths along the entities in the KG to provide a human-readable explanation for model prediction. KURIT-Net receives entity and relation trajectory embedding (RTE) and fully reflects potential interests of each user by summarizing all reasoning paths in a KG. Besides, we conduct extensive experiments on six public datasets, our KURIT-Net significantly outperforms state-of-the-art approaches and shows its interpretability in recommendation.

Framework

Experiment

Conclusion

We have proposed a KURIT-Net with UIMTs for routing knowledge. The derived knowledge-tree-routed user-interest trajectories enable our knowledge-aware model, KURIT-Net, to incorporate knowledge into the RS, aiming to explore potential interests of users for two recommendation tasks, i.e., CTR prediction and Top-K prediction. KURIT-Net learns the user embedding by considering ETE and RTE to improve the representation ability. The former aims to model a series of items selected previously by the user because the historical user interests affect directly the recommended item; the latter focuses on making the interaction between entities and relations for exploring the potential interests deeply. Extensive experiments are conducted on six recommendation benchmarks and demonstrate the effectiveness of our proposed method for recommendations. Befitting from UIMTs, the proposed KURIT-Net provides a new perspective of user interest embedding with knowledge-tree-routed trajectories for knowledge-graph-aware RS and explainable recommendations.

In future work, we plan to: 1) incorporate causal reasoning into the UIMT to infer user intention behind their behaviors and 2) devise a conversation module between the user and the RS for proactively elicit user preference to enhance the recommendation performance.