Zhejiang Lab, Hangzhou, 311121, China.
Harbin University of Science and Technology, Harbin, 150006, China.
Neural Netw. 2024 Dec;180:106601. doi: 10.1016/j.neunet.2024.106601. Epub 2024 Aug 8.
Knowledge graphs (KG) are vital for extracting and storing knowledge from large datasets. Current research favors knowledge graph-based recommendation methods, but they often overlook the features learning of relations between entities and focus excessively on entity-level details. Moreover, they ignore a crucial fact: the aggregation process of entity and relation features in KG is complex, diverse, and imbalanced. To address this, we propose a recommendation-oriented KG confidence-aware embedding technique. It introduces an information aggregation graph and a confidence feature aggregation mechanism to overcome these challenges. Additionally, we quantify entity confidence at the feature and category levels, improving the precision of embeddings during information propagation and aggregation. Our approach achieves significant improvements over state-of-the-art KG embedding-based recommendation methods, with up to 6.20% increase in AUC and 8.46% increase in GAUC, as demonstrated on four public KG datasets.
知识图谱（KG）对于从大型数据集提取和存储知识至关重要。目前的研究倾向于基于知识图谱的推荐方法，但它们往往忽略了实体之间关系的特征学习，过度关注实体级别的细节。此外，它们忽略了一个关键事实：KG 中实体和关系特征的聚合过程复杂、多样且不平衡。为了解决这个问题，我们提出了一种面向推荐的 KG 置信感知嵌入技术。它引入了信息聚合图和置信特征聚合机制来克服这些挑战。此外，我们在特征和类别级别量化了实体置信度，在信息传播和聚合过程中提高了嵌入的精度。我们的方法在四个公共的 KG 数据集上实现了对最先进的 KG 嵌入推荐方法的显著改进，AUC 提高了 6.20%，GAUC 提高了 8.46%。
