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
  • [21] Graph Embedding with Similarity Metric Learning
    Tao, Tao
    Wang, Qianqian
    Ruan, Yue
    Li, Xue
    Wang, Xiujun
    SYMMETRY-BASEL, 2023, 15 (08):
  • [22] A survey: knowledge graph entity alignment research based on graph embedding
    Zhu, Beibei
    Wang, Ruolin
    Wang, Junyi
    Shao, Fei
    Wang, Kerun
    ARTIFICIAL INTELLIGENCE REVIEW, 2024, 57 (09)
  • [23] Graph-theoretic System Decomposition Based on Modified Cosine-based Similarity
    Lu, Luheng
    Yang, Shipin
    Zhang, Yinqiang
    Guo, Peizhi
    Li, Lijuan
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 6237 - 6242
  • [24] Deep Interest Network Based on Knowledge Graph Embedding
    Zhang, Dehai
    Wang, Haoxing
    Yang, Xiaobo
    Ma, Yu
    Liang, Jiashu
    Ren, Anquan
    APPLIED SCIENCES-BASEL, 2023, 13 (01):
  • [25] Embedding-based approximate query for knowledge graph
    Qiu, Jingyi
    Zhang, Duxi
    Song, Aibo
    Wang, Honglin
    Zhang, Tianbo
    Jin, Jiahui
    Fang, Xiaolin
    Li, Yaqi
    Journal of Southeast University (English Edition), 2024, 40 (04) : 417 - 424
  • [26] Generalized Translation-Based Embedding of Knowledge Graph
    Ebisu, Takuma
    Ichise, Ryutaro
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2020, 32 (05) : 941 - 951
  • [27] Bootstrapped Knowledge Graph Embedding based on Neighbor Expansion
    Kim, Jun Seon
    Ahn, Seong Jin
    Kim, Myoung Ho
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022, 2022, : 4123 - 4127
  • [28] Embedding based Link Prediction for Knowledge Graph Completion
    Biswas, Russa
    CIKM '20: PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, 2020, : 3221 - 3224
  • [29] Knowledge Graph Embedding in Intent-Based Networking
    Mehmood, Kashif
    Kralevska, Katina
    Palma, David
    2024 IEEE 10TH INTERNATIONAL CONFERENCE ON NETWORK SOFTWARIZATION, NETSOFT 2024, 2024, : 13 - 18
  • [30] A review of recommender systems based on knowledge graph embedding
    Zhang, Jin-Cheng
    Zain, Azlan Mohd
    Zhou, Kai-Qing
    Chen, Xi
    Zhang, Ren-Min
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 250