高级检索
    王培妍, 段磊, 郭正山, 蒋为鹏, 张译丹. 基于张量分解的知识超图链接预测模型[J]. 计算机研究与发展, 2021, 58(8): 1599-1611. DOI: 10.7544/issn1000-1239.2021.20210315
    引用本文: 王培妍, 段磊, 郭正山, 蒋为鹏, 张译丹. 基于张量分解的知识超图链接预测模型[J]. 计算机研究与发展, 2021, 58(8): 1599-1611. DOI: 10.7544/issn1000-1239.2021.20210315
    Wang Peiyan, Duan Lei, Guo Zhengshan, Jiang Weipeng, Zhang Yidan. Knowledge Hypergraph Link Prediction Model Based on Tensor Decomposition[J]. Journal of Computer Research and Development, 2021, 58(8): 1599-1611. DOI: 10.7544/issn1000-1239.2021.20210315
    Citation: Wang Peiyan, Duan Lei, Guo Zhengshan, Jiang Weipeng, Zhang Yidan. Knowledge Hypergraph Link Prediction Model Based on Tensor Decomposition[J]. Journal of Computer Research and Development, 2021, 58(8): 1599-1611. DOI: 10.7544/issn1000-1239.2021.20210315

    基于张量分解的知识超图链接预测模型

    Knowledge Hypergraph Link Prediction Model Based on Tensor Decomposition

    • 摘要: 知识超图包含了现实世界中的事实,并给出这些事实的结构化表示.但知识超图无法包括所有事实,所以其是高度不完整的.链接预测方法致力于根据现有实体间链接推理缺失链接,因此广泛应用于知识库补全.目前大多数研究集中于二元关系知识图谱的补全.然而,现实世界中实体间的关系通常是非二元的,即关系中涉及的实体通常多于2个.相较于知识图谱,知识超图能够以一种灵活且自然的方式来表示这些复杂的多元关系.对此,设计一个基于张量分解的知识超图链接预测模型Typer,显式地为不同关系以及不同位置上实体的角色建模,并对关系进行细化分解以提升模型性能.同时,考虑到促进实体与关系间的信息流动有助于学习实体和关系的嵌入表示,提出窗口的概念,以增加实体与关系的交互.此外,证明了Typer模型具有完全表达性,并给出了使模型具有完全表达性的嵌入表示维度边界.在多个公开真实知识超图数据集上进行了详实的实验,实验表明Typer模型能有效解决知识超图链接预测问题,并在所有数据集上取得了较其他方法更好的结果.

       

      Abstract: Knowledge hypergraphs contain facts in the real world and provide a structured representation of these facts, but they cannot include all facts. They are highly incomplete. Link prediction approaches aim at inferring missing links based on existing links between entities, so they are widely used in knowledge base completion. At present, most researches focus on the completion of the binary relational knowledge graphs. However, the relations between entities in the real world usually go beyond pairwise associations, that is, there are more than two entities involved in a relation. Compared with knowledge graphs, knowledge hypergraphs can represent these complex n-ary relations in a flexible and natural way. Therefore, we propose a knowledge hypergraph link prediction model based on tensor decomposition, called Typer. It explicitly models the roles of entities in different relations and positions, and decomposes the relations to improve the performance. Meanwhile, considering that promoting the information flow between entities and relations is helpful for learning embeddings of entities and relations, we propose the concept of windows to increase the interaction between entities and relations. In addition, we prove Typer is fully expressive and derive a bound on the dimensionality of its embeddings for full expressivity. We conduct extensive experiments on multiple public real-world knowledge hypergraph datasets. Experiments show that Typer is effective for link prediction in knowledge hypergraphs and achieves better results on all benchmark datasets than other approaches.

       

    /

    返回文章
    返回