期刊
出版社
IEEE
DOI: 10.1109/IJCNN55064.2022.9892593
关键词
Knowledge Graph; Recommendation; Feature Interaction; Convolutional Neural Network; Attention Mechanism
类别
资金
- Gansu Natural Science Foundation Project [21JR7RA114]
- National Natural Science Foundation of China [61762078, 61363058, U1811264, 61966004]
- Northwest Normal University Young Teachers Research Capacity Promotion Plan [NWNU-LKQN2019-2]
- NWNU Graduate Research Project Funding Program [2021KYZZ02103]
This paper proposes a new method named KGID, which models fine-grained feature interaction and intent factors in KG-based GNN recommendation, significantly improving recommendation performance.
Knowledge Graph(KG) contains structured attribute information which has been widely utilized for recommendations, as well as can effectively tackle the sparsity and cold start problems of collaborative filtering. In recent years, Graph Neural Networks (GNNs) serve as a novel deep learning technique that can significantly enhance recommendation performance. Unfortunately, existing KG-based GNN models are coarse-grained ignoring i)effective high-order feature interaction and fusion mechanism and ii)interpretable user latent intent decomposition. In this paper, we propose a new method named Knowledge Graph recommendation model via high-order feature Interaction and intent Decomposition(KGID), which explicitly models the fine-grained feature interaction and intent factors in KG-based GNN recommendation. Initially, high-order feature interactions are captured via the two-granularity convolutional neural networks on the item side. Next, the implicit intent factor behind the user decisions is modeled by two-level attention mechanisms. Ultimately, user representations and item representations are augmented simultaneously. We conduct experiments on three benchmark datasets
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据