Relation-Aware Network with Attention-Based Loss for Few-Shot Knowledge Graph Completion

被引:0
|
作者
Qiao, Qiao [1 ]
Li, Yuepei [1 ]
Kang, Li [1 ]
Li, Qi [1 ]
机构
[1] Iowa State Univ, Ames, IA 50011 USA
关键词
Few-shot learning; Knowledge graph completion;
D O I
10.1007/978-3-031-33380-4_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Few-shot knowledge graph completion (FKGC) task aims to predict unseen facts of a relation with few-shot reference entity pairs. Current approaches randomly select one negative sample for each reference entity pair to minimize a margin-based ranking loss, which easily leads to a zero-loss problem if the negative sample is far away from the positive sample and then out of the margin. Moreover, the entity should have a different representation under a different context. To tackle these issues, we propose a novel Relation-Aware Network with Attention-Based Loss (RANA) framework. Specifically, to better utilize the plentiful negative samples and alleviate the zero-loss issue, we strategically select relevant negative samples and design an attention-based loss function to further differentiate the importance of each negative sample. The intuition is that negative samples more similar to positive samples will contribute more to the model. Further, we design a dynamic relation-aware entity encoder for learning a context-dependent entity representation. Experiments demonstrate that RANA outperforms the state-of-the-art models on two benchmark datasets.
引用
收藏
页码:99 / 111
页数:13
相关论文
共 50 条
  • [1] Implicit relational attention network for few-shot knowledge graph completion
    Yang, Xu-Hua
    Li, Qi-Yao
    Wei, Dong
    Long, Hai-Xia
    [J]. APPLIED INTELLIGENCE, 2024, 54 (08) : 6433 - 6443
  • [2] Few-Shot Knowledge Graph Completion Model Based on Relation Learning
    Li, Weijun
    Gu, Jianlai
    Li, Ang
    Gao, Yuxiao
    Zhang, Xinyong
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (17):
  • [3] Few-Shot Knowledge Graph Completion
    Zhang, Chuxu
    Yao, Huaxiu
    Huang, Chao
    Jiang, Meng
    Li, Zhenhui
    Chawla, Nitesh, V
    [J]. THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 3041 - 3048
  • [4] REFORM: Error-Aware Few-Shot Knowledge Graph Completion
    Wang, Song
    Huang, Xiao
    Chen, Chen
    Wu, Liang
    Li, Jundong
    [J]. PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 1979 - 1988
  • [5] Adaptive Attentional Network for Few-Shot Knowledge Graph Completion
    Sheng, Jiawei
    Guo, Shu
    Chen, Zhenyu
    Yue, Juwei
    Wang, Lihong
    Liu, Tingwen
    Xu, Hongbo
    [J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 1681 - 1691
  • [6] Twin Graph Attention Network with Evolution Pattern Learner for Few-Shot Temporal Knowledge Graph Completion
    Liang, Yi
    Zhao, Shuai
    Cheng, Bo
    Yang, Hao
    [J]. KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT I, KSEM 2023, 2023, 14117 : 234 - 246
  • [7] A survey of few-shot knowledge graph completion
    Zhang, Chaoqin
    Li, Ting
    Yin, Yifeng
    Ma, Jiangtao
    Gan, Yong
    Zhang, Yanhua
    Qiao, Yaqiong
    [J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2023, 45 (04) : 6127 - 6143
  • [8] Semantic Interaction Matching Network for Few-Shot Knowledge Graph Completion
    Luo, Pengfei
    Zhu, Xi
    Xu, Tong
    Zheng, Yi
    Chen, Enhong
    [J]. ACM TRANSACTIONS ON THE WEB, 2024, 18 (02)
  • [9] Adaptive Prototype Interaction Network for Few-Shot Knowledge Graph Completion
    Li, Yuling
    Yu, Kui
    Zhang, Yuhong
    Liang, Jiye
    Wu, Xindong
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, : 1 - 14
  • [10] RAGAT: Relation Aware Graph Attention Network for Knowledge Graph Completion
    Liu, Xiyang
    Tan, Huobin
    Chen, Qinghong
    Lin, Guangyan
    [J]. IEEE ACCESS, 2021, 9 : 20840 - 20849