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
收藏
页码:1 / 12
页数:12
相关论文
共 50 条
  • [21] Graph attention network with dynamic representation of relations for knowledge graph completion
    Zhang, Xin
    Zhang, Chunxia
    Guo, Jingtao
    Peng, Cheng
    Niu, Zhendong
    Wu, Xindong
    EXPERT SYSTEMS WITH APPLICATIONS, 2023, 219
  • [22] An Overview of Research on Knowledge Graph Completion Based on Graph Neural Network
    Yue W.
    Haichun S.
    Data Analysis and Knowledge Discovery, 2024, 8 (03) : 10 - 28
  • [23] Relational Graph Neural Network with Hierarchical Attention for Knowledge Graph Completion
    Zhang, Zhao
    Zhuang, Fuzhen
    Zhu, Hengshu
    Shi, Zhiping
    Xiong, Hui
    He, Qing
    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 : 9612 - 9619
  • [24] Learnable convolutional attention network for knowledge graph completion
    Shang, Bin
    Zhao, Yinliang
    Liu, Jun
    KNOWLEDGE-BASED SYSTEMS, 2024, 285
  • [25] TDN: Triplet Distributor Network for Knowledge Graph Completion
    Wang, Jiapu
    Wang, Boyue
    Gao, Junbin
    Li, Xiaoyan
    Hu, Yongli
    Yin, Baocai
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (12) : 13002 - 13014
  • [26] Translating Embeddings for Knowledge Graph Completion with Relation Attention Mechanism
    Qian, Wei
    Fu, Cong
    Zhu, Yu
    Cai, Deng
    He, Xiaofei
    PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 4286 - 4292
  • [27] ProjFE: Prediction of fuzzy entity and relation for knowledge graph completion
    Liu, Huajing
    Bai, Luyi
    Ma, Xiangnan
    Yu, Wenting
    Xu, Changming
    APPLIED SOFT COMPUTING, 2019, 81
  • [28] Representation Learning with Ordered Relation Paths for Knowledge Graph Completion
    Zhu, Yao
    Liu, Hongzhi
    Wu, Zhonghai
    Song, Yang
    Zhang, Tao
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 2662 - 2671
  • [29] Knowledge Graph Completion Model Based on Entity and Relation Fusion
    Zhengang Z.
    Chuanming Y.
    Data Analysis and Knowledge Discovery, 2023, 7 (02): : 15 - 25
  • [30] Hamming Distance Encoding Multihop Relation Knowledge Graph Completion
    Chen, Panfeng
    Wang, Yisong
    Yu, Quan
    Fan, Yi
    Feng, Renyan
    IEEE ACCESS, 2020, 8 : 117146 - 117158