RoCS: Knowledge Graph Embedding Based on Joint Cosine Similarity

被引:5
|
作者
Wang, Lifeng [1 ]
Luo, Juan [1 ]
Deng, Shiqiao [1 ]
Guo, Xiuyuan [2 ]
机构
[1] Hunan Univ, Sch Comp Sci & Elect Engn, LW, JL, Changsha 410000, Peoples R China
[2] Hunan Univ, Sch Journalism & Commun, Changsha 410000, Peoples R China
基金
中国国家自然科学基金;
关键词
complex vectors; embedding; joint cosine similarity; knowledge graphs; scoring function; unbounded;
D O I
10.3390/electronics13010147
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Knowledge graphs usually have many missing links, and predicting the relationships between entities has become a hot research topic in recent years. Knowledge graph embedding research maps entities and relations to a low-dimensional continuous space representation to predict links between entities. The present research shows that the key to the knowledge graph embedding approach is the design of scoring functions. According to the scoring function, knowledge graph embedding methods can be classified into dot product models and distance models. We find that the triple scores obtained using the dot product model or the distance model were unbounded, which leads to large variance. In this paper, we propose RotatE Cosine Similarity (RoCS), a method to compute the joint cosine similarity of complex vectors as a scoring function to make the triple scores bounded. Our approach combines the rotational properties of the complex vector embedding model RotatE to model complex relational patterns. The experimental results demonstrate that the newly introduced RoCS yields substantial enhancements compared to RotatE across various knowledge graph benchmarks, improving up to 4.0% in hits at 1 (Hits@1) on WN18RR and improving up to 3.3% in Hits@1 on FB15K-237. Meanwhile, our method achieves some new state-of-the-art (SOTA), including Hits@3 of 95.6%, Hits@10 of 96.4% on WN18, and mean reciprocal rank (MRR) of 48.9% and Hits@1 of 44.5% on WN18RR.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Knowledge Graph Representation via Similarity-Based Embedding
    Tan, Zhen
    Zhao, Xiang
    Fang, Yang
    Ge, Bin
    Xiao, Weidong
    SCIENTIFIC PROGRAMMING, 2018, 2018
  • [2] Entity Similarity-Based Negative Sampling for Knowledge Graph Embedding
    Yao, Naimeng
    Liu, Qing
    Li, Xiang
    Yang, Yi
    Bai, Quan
    PRICAI 2022: TRENDS IN ARTIFICIAL INTELLIGENCE, PT II, 2022, 13630 : 73 - 87
  • [3] Similarity Analysis of Knowledge Graph-based Company Embedding for Stocks Portfolio
    Zhang, Boyao
    Li, Zhongrui
    Yang, Chao
    Wang, Zongguo
    Zhao, Yonghua
    Sun, Jingqi
    Wang, Lihua
    2021 IEEE 6TH INTERNATIONAL CONFERENCE ON SMART CLOUD (SMARTCLOUD 2021), 2021, : 84 - 89
  • [4] Machining Scheme Selection of Features Based on Process Knowledge Graph and Improved Cosine Similarity Matching
    Wang, Lin
    Cheng, Hao
    Wang, Rui
    Huang, Xunzhuo
    MACHINES, 2025, 13 (03)
  • [5] Similarity attributed knowledge graph embedding enhancement for item recommendation
    Khan, Nasrullah
    Ma, Zongmin
    Ullah, Aman
    Polat, Kemal
    INFORMATION SCIENCES, 2022, 613 : 69 - 95
  • [6] Cosine-Based Embedding for Completing Schematic Knowledge
    Gao, Huan
    Zheng, Xianda
    Li, Weizhuo
    Qi, Guilin
    Wang, Meng
    NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING (NLPCC 2019), PT I, 2019, 11838 : 249 - 261
  • [7] Graph Embedding Based Recommendation Techniques on the Knowledge Graph
    Grad-Gyenge, Laszlo
    Kiss, Attila
    Filzmoser, Peter
    ADJUNCT PUBLICATION OF THE 25TH CONFERENCE ON USER MODELING, ADAPTATION AND PERSONALIZATION (UMAP'17), 2017, : 354 - 359
  • [8] Research on Knowledge Graph Completion Based upon Knowledge Graph Embedding
    Feng, Tuoyu
    Wu, Yongsheng
    Li, Libing
    2024 9TH INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS, ICCCS 2024, 2024, : 1335 - 1342
  • [9] Learning Patient Similarity via Heterogeneous Medical Knowledge Graph Embedding
    Lin, Zhihuang
    Yang, Dan
    Jiang, Hua
    Yin, Hang
    IAENG International Journal of Computer Science, 2021, 48 (04)
  • [10] JECI: A Joint Knowledge Graph Embedding Model for Concepts and Instances
    Zhou, Jing
    Wang, Peng
    Pan, Zhe
    Xu, Zhongkai
    SEMANTIC TECHNOLOGY, JIST 2019: PROCEEDINGS, 2020, 12032 : 82 - 98