<p>Knowledge graph-based recommender systems have attracted increasing attention in recent years. By extracting the semantics of entities and relationships, these recommender systems enable a more comprehensive understanding of user preferences. However, existing methods overlook the impact of low-quality links in knowledge graphs, which leads to user preference propagation bias and affects recommendation accuracy. In this paper, we propose RKR-GAT, a recurrent knowledge-aware recommendation algorithm based on a graph attention network (GAT). Specifically, RKR-GAT integrates user–item graphs and the knowledge graph into a unified graph and learns node embeddings using a graph attention network. To alleviate the issue of user preference propagation bias, we design a new path filtering module to reject low-quality connections and adaptively retain valid reasoning paths between users and items in the knowledge graph. Furthermore, RKR-GAT combines recurrent neural networks with a self-attention mechanism to efficiently analyze the semantics of the paths to generate more accurate recommendations while providing explainability. Ultimately, experimental results on three public datasets demonstrate the better performance of RKR-GAT compared to state-of-the-art baselines.</p>