Representation Learning of Knowledge Graphs with Multi-scale Capsule Network

被引:1
|
作者
Cheng, Jingwei [1 ]
Yang, Zhi [1 ]
Dang, Jinming [1 ]
Pan, Chunguang [1 ]
Zhang, Fu [1 ]
机构
[1] Northeastern Univ, Coll Comp Sci & Engn, Shenyang, Peoples R China
来源
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2019, PT I | 2019年 / 11871卷
基金
中国国家自然科学基金;
关键词
Representation learning; Capsule network; Multi-scale; Dynamic routing; Knowledge graph completion;
D O I
10.1007/978-3-030-33607-3_31
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Representation learning of knowledge graphs has gained wide attention in the field of natural language processing. Most existing knowledge representation models for knowledge graphs embed triples into a continuous low-dimensional vector space through a simple linear transformation. In spite of high computation efficiency, the fitting ability of these models is suboptimal. In this paper, we propose a multi-scale capsule network to model relations between embedding vectors from a deep perspective. We use convolution kernels with different sizes of windows in the convolutional layer inside a Capsule network to extract semantic features of entities and relations in triples. These semantic features are then represented as a continuous vector through a routing process algorithm in the capsule layer. The modulus of this vector is used as the score of confidence of correctness of a triple. Experiments show that the proposed model obtains better performance than state-of-the-art embedding models for the task of knowledge graph completion over two benchmarks, WN18RR and FB15k-237.
引用
收藏
页码:282 / 290
页数:9
相关论文
共 50 条
  • [1] SelectE: Multi-scale adaptive selection network for knowledge graph representation learning
    Zu, Lizheng
    Lin, Lin
    Fu, Song
    Guo, Feng
    Wu, Jinlei
    KNOWLEDGE-BASED SYSTEMS, 2024, 291
  • [2] Knowledge Graph Representation Learning With Multi-Scale Capsule-Based Embedding Model Incorporating Entity Descriptions
    Cheng, Jingwei
    Zhang, Fu
    Yang, Zhi
    IEEE ACCESS, 2020, 8 : 203028 - 203038
  • [3] Multi-Scale Neural Network for EEG Representation Learning in BCI
    Ko, Wonjun
    Jeon, Eunjin
    Jeong, Seungwoo
    Suk, Heung-Il
    IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2021, 16 (02) : 31 - 45
  • [4] A PARAMETER EFFICIENT MULTI-SCALE CAPSULE NETWORK
    Jeong, Minki
    Kim, Changick
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 739 - 743
  • [5] Multi-Scale Representation Learning on Proteins
    Somnath, Vignesh Ram
    Bunne, Charlotte
    Krause, Andreas
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [6] Dynamic multi-scale feature augmentation for inductive network representation learning
    Cui, Shicheng
    Li, Deqiang
    Zhang, Jing
    PATTERN RECOGNITION, 2025, 161
  • [7] MSEN: A Multi-Scale Evolutionary Network for Modeling the Evolution of Temporal Knowledge Graphs
    Yu, Yong
    Chen, Shudong
    Du, Rong
    Tong, Da
    Xu, Hao
    Chen, Shuai
    FUTURE INTERNET, 2023, 15 (10)
  • [8] Knowledge Representation for Multi-Scale Physiology Route Modeling
    Kokash, Natallia
    de Bono, Bernard
    FRONTIERS IN NEUROINFORMATICS, 2021, 15
  • [9] Multi-scale capsule generative adversarial network for snow removal
    Yang, Fei
    Zhang, Jialu
    Zhang, Qian
    IET COMPUTER VISION, 2021, 15 (07) : 474 - 486
  • [10] MS-CapsNet: A Novel Multi-Scale Capsule Network
    Xiang, Canqun
    Zhang, Lu
    Tang, Yi
    Zou, Wenbin
    Xu, Chen
    IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (12) : 1850 - 1854