Relation Adversarial Network for Low Resource Knowledge Graph Completion

被引:41
|
作者
Zhang, Ningyu [1 ,2 ]
Deng, Shumin [2 ,3 ]
Sun, Zhanlin [4 ]
Chen, Jiaoyan [5 ]
Zhang, Wei [1 ,2 ]
Chen, Huajun [2 ,3 ]
机构
[1] Alibaba Grp, Hangzhou, Peoples R China
[2] AZFT Joint Lab Knowledge Engine, Hangzhou, Peoples R China
[3] Zhejiang Univ, Hangzhou, Peoples R China
[4] Carnegie Mellon Univ, Sch Comp Sci, Pittsburgh, PA 15213 USA
[5] Univ Oxford, Dept Comp Sci, Oxford, England
关键词
Knowledge Graphs; Low Resource Knowledge Graph Completion; Adversarial Transfer Learning; Link Prediction; Relation Extraction;
D O I
10.1145/3366423.3380089
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 Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.
引用
下载
收藏
页码:1 / 12
页数:12
相关论文
共 50 条
  • [1] Low-Resource Knowledge Graph Completion by Combining Entity and Relation Message Passing
    Zhang, Ting
    Du, Fang
    Song, Lijuan
    Shi, Yingjie
    Zhao, Guodong
    Li, Ting
    Computer Engineering and Applications, 2024, 60 (22) : 137 - 144
  • [2] RAGAT: Relation Aware Graph Attention Network for Knowledge Graph Completion
    Liu, Xiyang
    Tan, Huobin
    Chen, Qinghong
    Lin, Guangyan
    IEEE ACCESS, 2021, 9 : 20840 - 20849
  • [3] Negative Sampling for Knowledge Graph Completion Based on Generative Adversarial Network
    Le, Thanh
    Pham, Trinh
    Le, Bac
    COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2021), 2021, 12876 : 3 - 15
  • [4] Sequence Embedding for Zero or Low Resource Knowledge Graph Completion
    Du, Zhijuan
    DATABASE SYSTEMS FOR ADVANCED APPLICATIONS (DASFAA 2021), PT I, 2021, 12681 : 290 - 306
  • [5] Semantic- and relation-based graph neural network for knowledge graph completion
    Li, Xinlu
    Tian, Yujie
    Ji, Shengwei
    APPLIED INTELLIGENCE, 2024, 54 (08) : 6085 - 6107
  • [6] Knowledge Collaborative Fine-tuning for Low-resource Knowledge Graph Completion
    Zhang N.-Y.
    Xie X.
    Chen X.
    Deng S.-M.
    Ye H.-B.
    Chen H.-J.
    Ruan Jian Xue Bao/Journal of Software, 2022, 33 (10): : 3531 - 3545
  • [7] RoAN: A relation-oriented attention network for temporal knowledge graph completion
    Bai, Luyi
    Ma, Xiangnan
    Meng, Xiangxi
    Ren, Xin
    Ke, Yujing
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [8] ParamE: Regarding Neural Network Parameters as Relation Embeddings for Knowledge Graph Completion
    Che, Feihu
    Zhang, Dawei
    Tao, Jianhua
    Niu, Mingyue
    Zhao, Bocheng
    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 : 2774 - 2781
  • [9] Modeling Relation Paths for Knowledge Graph Completion
    Shen, Ying
    Ding, Ning
    Zheng, Hai-Tao
    Li, Yaliang
    Yang, Min
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2021, 33 (11) : 3607 - 3617
  • [10] Discriminator-based adversarial networks for knowledge graph completion
    Tubaishat, Abdallah
    Zia, Tehseen
    Faiz, Rehana
    Al Obediat, Feras
    Shah, Babar
    Windridge, David
    NEURAL COMPUTING & APPLICATIONS, 2023, 35 (11): : 7975 - 7987