Explainable Reasoning over Knowledge Graphs for Recommendation

TLDR

In recent years, recommender systems have increasingly incorporated knowledge graphs, using graph connectivity to uncover user–item paths that reveal entity semantics and better capture user interests. This work proposes the Knowledgeaware Path Recurrent Network (KPRN) to better infer user preferences by modeling sequential dependencies and holistic semantics of knowledge‑graph paths. KPRN constructs path embeddings by composing entity and relation semantics, models their sequential dependencies, and applies weighted pooling to prioritize informative paths, providing explainable recommendations. Experiments on movie and music datasets show KPRN significantly outperforms state‑of‑the‑art baselines such as Collaborative Knowledge Base Embedding and Neural Factorization Machine.

Abstract

Incorporating knowledge graph into recommender systems has attracted increasing attention in recent years. By exploring the interlinks within a knowledge graph, the connectivity between users and items can be discovered as paths, which provide rich and complementary information to user-item interactions. Such connectivity not only reveals the semantics of entities and relations, but also helps to comprehend a user’s interest. However, existing efforts have not fully explored this connectivity to infer user preferences, especially in terms of modeling the sequential dependencies within and holistic semantics of a path.In this paper, we contribute a new model named Knowledgeaware Path Recurrent Network (KPRN) to exploit knowledge graph for recommendation. KPRN can generate path representations by composing the semantics of both entities and relations. By leveraging the sequential dependencies within a path, we allow effective reasoning on paths to infer the underlying rationale of a user-item interaction. Furthermore, we design a new weighted pooling operation to discriminate the strengths of different paths in connecting a user with an item, endowing our model with a certain level of explainability. We conduct extensive experiments on two datasets about movie and music, demonstrating significant improvements over state-of-the-art solutions Collaborative Knowledge Base Embedding and Neural Factorization Machine.