ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Knowledge graph embedding model with attention-based high-low level features interaction convolutional network

Wang, Jingxiong; Zhang, Qi; Shi, Fobo*; Li, Duantengchuan*; Cai, Yuefeng; Wang, Jian; Li, Bing; Wang, Xiaoguang; Zhang, Zhen; Zheng, Chao武汉大学
INFORMATION PROCESSING & MANAGEMENT2023-7DOI: 10.1016/j.ipm.2023.103350
7被引11阅读
引用收藏
分享

摘要

Knowledge graphs are sizeable graph-structured knowledge with both abstract and concrete concepts in the form of entities and relations. Recently, convolutional neural networks have achieved outstanding results for more expressive representations of knowledge graphs. However, existing deep learning-based models exploit semantic information from single-level feature interaction, potentially limiting expressiveness. We propose a knowledge graph embedding model with an attention-based high-low level features interaction convolutional network called ConvHLE to alleviate this issue. This model effectively harvests richer semantic information and generates more expressive representations. Concretely, the multilayer convolutional neural network is utilized to fuse high-low level features. Then, features in fused feature maps interact with other informative neighbors through the criss-cross attention mechanism, which expands the receptive fields and boosts the quality of interactions. Finally, a plausibility score function is proposed for the evaluation of our model. The performance of ConvHLE is experimentally investigated on six benchmark datasets with individual characteristics. Extensive experimental results prove that ConvHLE learns more expressive and discriminative feature representations and has outperformed other state-of-the-art baselines over most metrics when addressing link prediction tasks. Comparing MRR and Hits@1 on FB15K-237, our model outperforms the baseline ConvE by 13.5% and 16.0%, respectively.

学科与关键词

关键词
Link predictionKnowledge graph embeddingConvolutional neural networkCriss-cross attention mechanismHigh-low level features interaction
相关
加载中…
  • Enhancing the convolution-based knowledge graph embeddings by increasing dimension-wise interactions*
    Lu, Fengyuan; Zhou, Jie; Huang, Xinli*DATA & KNOWLEDGE ENGINEERING, 2023, 146: 102184.
  • A lightweight CNN-based knowledge graph embedding model with channel attention for link prediction
    Zhou, Xin*; Guo, Jingnan; Jiang, Liling; Ning, Bo; Wang, YanhaoMathematical Biosciences and Engineering, 2023, 20(6): 9607-9624.
  • Recalibration convolutional networks for learning interaction knowledge graph embedding
    Li, Zhifei; Liu, Hai*; Zhang, Zhaoli; Liu, Tingting; Shu, JiangboNEUROCOMPUTING, 2021, 427: 118-130.被引 27
查看全部 →

发表信息

论文状态
公开发表
期刊
INFORMATION PROCESSING & MANAGEMENT
发表日期
2023-07
卷期
第 60 卷, 第 4 期
页码
103350
DOI
10.1016/j.ipm.2023.103350
语言
ENGLISH
成果收录
SSCI · SCIE
资助标注
Major Project of the National Social Science Fund [62032016]; National Natural Science Foundation of China [2021BAA031]; Key Research and Development Program of Hubei Province [2022S10]; Scientific Research Fund for Young Teachers of Wuhan Sports University; [21ZD334]

作者

  • W

    Wang, Jingxiong (第一作者)

  • Z

    Zhang, Qi

    cent china normal univ

查看全部 10 位作者收起作者
  • S

    Shi, Fobo (通讯)

    cent china normal univ

  • L

    Li, Duantengchuan (通讯)

    wuhan univ

  • C

    Cai, Yuefeng

    zte corp

  • W

    Wang, Jian

  • L

    Li, Bing

    wuhan univ

  • W

    Wang, Xiaoguang

    wuhan univ

  • Z

    Zhang, Zhen

    wuhan sports univ · wuhan univ

  • Z

    Zheng, Chao

    wuhan univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417