College of Computer Science and Technology, Jilin University, Changchun, China.
Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, China.
PLoS One. 2021 Oct 28;16(10):e0258410. doi: 10.1371/journal.pone.0258410. eCollection 2021.
To alleviate the data sparsity and cold start problems for collaborative filtering in recommendation systems, side information is usually leveraged by researchers to improve the recommendation performance. The utility of knowledge graph regards the side information as part of the graph structure and gives an explanation for recommendation results. In this paper, we propose an enhanced multi-task neighborhood interaction (MNI) model for recommendation on knowledge graphs. MNI explores not only the user-item interaction but also the neighbor-neighbor interactions, capturing a more sophisticated local structure. Besides, the entities and relations are also semantically embedded. And with the cross&compress unit, items in the recommendation system and entities in the knowledge graph can share latent features, and thus high-order interactions can be investigated. Through extensive experiments on real-world datasets, we demonstrate that MNI outperforms some of the state-of-the-art baselines both for CTR prediction and top-N recommendation.
为了缓解推荐系统中协同过滤的稀疏性和冷启动问题，研究人员通常会利用侧信息来提高推荐性能。知识图谱的作用是将侧信息作为图结构的一部分，并为推荐结果提供解释。在本文中，我们提出了一种基于知识图的增强型多任务邻域交互（MNI）推荐模型。MNI 不仅探索了用户-项目交互，还探索了邻居-邻居交互，从而捕获了更复杂的局部结构。此外，实体和关系也被语义嵌入。通过交叉和压缩单元，推荐系统中的项目和知识图谱中的实体可以共享潜在特征，从而可以研究高阶交互。通过在真实数据集上的广泛实验，我们证明 MNI 在 CTR 预测和 top-N 推荐方面均优于一些最先进的基线。
