Federated knowledge graph completion via embedding-contrastive learning

被引:9
|
作者
Chen, Mingyang [1 ]
Zhang, Wen [2 ]
Yuan, Zonggang [3 ]
Jia, Yantao [3 ]
Chen, Huajun [1 ,4 ,5 ]
机构
[1] Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Peoples R China
[2] Zhejiang Univ, Sch Software Technol, Hangzhou, Peoples R China
[3] Huawei Technol Co Ltd, Shenzhen, Peoples R China
[4] Alibaba Zhejiang Univ Joint Inst Frontier Technol, Hangzhou, Peoples R China
[5] ZJU Hangzhou Global Sci & Technol Innovat Ctr, Hangzhou, Peoples R China
关键词
Knowledge graph embedding; Knowledge graph; Federated learning;
D O I
10.1016/j.knosys.2022.109459
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, the research about knowledge graphs (KGs) which contain a large number of triples, has gained massive attention. Many knowledge graph embedding methods are proposed to tackle the knowledge graph completion task. In real applications, knowledge graphs are applied not only in a centralized way but also in a decentralized manner. We study the problem of learning knowledge graph embeddings for a set of federated knowledge graphs, where their raw triples are not allowed to be collected together. We propose a federated learning framework FedEC. In our framework, a local training procedure is responsible for learning knowledge graph embeddings on each client based on a specific embedding learner. We apply embedding-contrastive learning to limit the embedding update for tackling data heterogeneity. Moreover, a global update procedure is used for sharing and averaging entity embeddings on the master server. Furthermore, we design embedding ensemble procedures to take full advantage of knowledge learned from different aspects. Finally, we conduct extensive experiments on datasets derived from KGE benchmark datasets, and the results show the effectiveness of our proposed model. (c) 2022 Elsevier B.V. All rights reserved.
引用
收藏
页数:10
相关论文
共 50 条
  • [1] Federated Knowledge Graph Completion via Latent Embedding Sharing and Tensor Factorization
    Wang, Maolin
    Zeng, Dun
    Xu, Zenglin
    Gut, Ruocheng
    Zhao, Xiangyu
    [J]. 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING, ICDM 2023, 2023, : 1361 - 1366
  • [2] Multi-view Contrastive Multiple Knowledge Graph Embedding for Knowledge Completion
    Kurokawa, Mori
    Yonekawa, Kei
    Haruta, Shuichiro
    Konishi, Tatsuya
    Asoh, Hideki
    Ono, Chihiro
    Hagiwara, Masafumi
    [J]. 2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, : 1412 - 1418
  • [3] Learning Embedding for Knowledge Graph Completion with Hypernetwork
    Le, Thanh
    Nguyen, Duy
    Le, Bac
    [J]. COMPUTATIONAL COLLECTIVE INTELLIGENCE (ICCCI 2021), 2021, 12876 : 16 - 28
  • [4] A contrastive knowledge graph embedding model with hierarchical attention and dynamic completion
    Shang, Bin
    Zhao, Yinliang
    Liu, Jun
    Liu, Yifan
    Wang, Chenxin
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (20): : 15005 - 15018
  • [5] A contrastive knowledge graph embedding model with hierarchical attention and dynamic completion
    Bin Shang
    Yinliang Zhao
    Jun Liu
    Yifan Liu
    Chenxin Wang
    [J]. Neural Computing and Applications, 2023, 35 : 15005 - 15018
  • [6] TCKGE: Transformers with contrastive learning for knowledge graph embedding
    Zhang, Xiaowei
    Fang, Quan
    Hu, Jun
    Qian, Shengsheng
    Xu, Changsheng
    [J]. INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL, 2022, 11 (04) : 589 - 597
  • [7] TCKGE: Transformers with contrastive learning for knowledge graph embedding
    Xiaowei Zhang
    Quan Fang
    Jun Hu
    Shengsheng Qian
    Changsheng Xu
    [J]. International Journal of Multimedia Information Retrieval, 2022, 11 : 589 - 597
  • [8] GFedKG: GNN-based federated embedding model for knowledge graph completion
    Wang, Yuzhuo
    Wang, Hongzhi
    Liu, Xianglong
    Yan, Yu
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 301
  • [9] Disentangled Relational Graph Neural Network with Contrastive Learning for knowledge graph completion
    Yin, Hong
    Zhong, Jiang
    Li, Rongzhen
    Li, Xue
    [J]. KNOWLEDGE-BASED SYSTEMS, 2024, 295
  • [10] Federated Knowledge Graph Embedding Unlearning via Diffusion Model
    Liu, Bingchen
    Fang, Yuanyuan
    Wang, Xu
    Li, Xin
    [J]. WEB AND BIG DATA, APWEB-WAIM 2024, PT II, 2024, 14962 : 272 - 286