Recommendation systems, as widely implemented nowadays on various platforms, recommend relevant items to users based on their preferences. The classical methods which rely on user-item interaction matrices has limitations, especially in scenarios where there is a lack of interaction data for new items. Knowledge graph (KG)-based recommendation systems have emerged as a promising solution. However, most KG-based methods adopt node embeddings, which do not provide personalized recommendations for different users and cannot generalize well to the new items. To address these limitations, we propose Knowledge-enhanced User-Centric subgraph Network (KUCNet), a subgraph learning approach with graph neural network (GNN) for effective recommendation. KUCNet constructs a U-I subgraph for each user-item pair that captures both the historical information of user-item interactions and the side information provided in KG. An attention-based GNN is designed to encode the U-I subgraphs for recommendation. Considering efficiency, the pruned user-centric computation graph is further introduced such that multiple U-I subgraphs can be simultaneously computed and that the size can be pruned by Personalized PageRank. Our proposed method achieves accurate, efficient, and interpretable recommendations especially for new items. Experimental results demonstrate the superiority of KUCNet over state-of-the-art KG-based and collaborative filtering (CF)-based methods.

翻译：推荐系统如今已在各类平台广泛应用，能根据用户偏好推荐相关物品。传统方法依赖用户-物品交互矩阵，但在新物品缺乏交互数据的场景下存在局限性。基于知识图谱（KG）的推荐系统已成为一种有前景的解决方案。然而，多数KG方法采用节点嵌入，未能为不同用户提供个性化推荐，且对新增物品的泛化能力不足。为克服这些局限，我们提出知识增强的用户中心子图网络（KUCNet）——一种基于图神经网络（GNN）的子图学习方法用于高效推荐。KUCNet为每个用户-物品对构建U-I子图，同时捕获用户-物品交互的历史信息和KG中的辅助信息。我们设计了一种基于注意力机制的GNN对U-I子图进行编码以实现推荐。为提升效率，进一步引入剪枝的用户中心计算图，使得多个U-I子图可同步计算，并通过个性化PageRank实现子图规模剪枝。所提方法尤其对新物品能实现准确、高效且可解释的推荐。实验结果表明，KUCNet在性能上优于当前最先进的基于KG和基于协同过滤（CF）的方法。