Continual Learning of Knowledge Graph Embeddings

被引:27
|
作者
Daruna, Angel [1 ]
Gupta, Mehul [1 ]
Sridharan, Mohan [2 ]
Chernova, Sonia [1 ]
机构
[1] Georgia Inst Technol, Atlanta, GA 30332 USA
[2] Univ Birmingham, Birmingham, W Midlands, England
基金
美国国家科学基金会;
关键词
Robots; Knowledge engineering; Semantics; Task analysis; Learning systems; Neural networks; Training; Continual learning; representation learning; FRAMEWORK;
D O I
10.1109/LRA.2021.3056071
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
In recent years, there has been a resurgence in methods that use distributed (neural) representations to represent and reason about semantic knowledge for robotics applications. However, while robots often observe previously unknown concepts, these representations typically assume that all concepts are known a priori, and incorporating new information requires all concepts to be learned afresh. Our work relaxes this limiting assumption of existing representations and tackles the incremental knowledge graph embedding problem by leveraging the principles of a range of continual learning methods. Through an experimental evaluation with several knowledge graphs and embedding representations, we provide insights about trade-offs for practitioners to match a semantics-driven robotics applications to a suitable continual knowledge graph embedding method.
引用
收藏
页码:1128 / 1135
页数:8
相关论文
共 50 条
  • [1] Enriching Translation-Based Knowledge Graph Embeddings Through Continual Learnings
    Song, Hyun-Je
    Park, Seong-Bae
    IEEE ACCESS, 2018, 6 : 60489 - 60497
  • [2] Learning Knowledge Graph Embeddings with Type Regularizer
    Kotnis, Bhushan
    Nastase, Vivi
    K-CAP 2017: PROCEEDINGS OF THE KNOWLEDGE CAPTURE CONFERENCE, 2017,
  • [3] Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning
    Zhang, Wen
    Paudel, Bibek
    Wang, Liang
    Chen, Jiaoyan
    Zhu, Hai
    Zhang, Wei
    Bernstein, Abraham
    Chen, Huajun
    WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019), 2019, : 2366 - 2377
  • [4] Fast and Accurate Learning of Knowledge Graph Embeddings at Scale
    Gupta, Udit
    Vadhiyar, Sathish
    2019 IEEE 26TH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING, DATA, AND ANALYTICS (HIPC), 2019, : 173 - 182
  • [5] Learning Knowledge Graph Embeddings via Generalized Hyperplanes
    Zhu, Qiannan
    Zhou, Xiaofei
    Tan, JianLong
    Liu, Ping
    Guo, Li
    COMPUTATIONAL SCIENCE - ICCS 2018, PT I, 2018, 10860 : 624 - 638
  • [6] Learning Entity and Relation Embeddings for Knowledge Graph Completion
    Lin, Yankai
    Liu, Zhiyuan
    Sun, Maosong
    Liu, Yang
    Zhu, Xuan
    PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 2181 - 2187
  • [7] Learning Entity Type Embeddings for Knowledge Graph Completion
    Moon, Changsung
    Jones, Paul
    Samatova, Nagiza F.
    CIKM'17: PROCEEDINGS OF THE 2017 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2017, : 2215 - 2218
  • [8] Distilling Knowledge Based on Curriculum Learning for Temporal Knowledge Graph Embeddings
    Zhang, Bin
    Li, Jiayin
    Dai, Yuanfei
    PROCEEDINGS OF THE 33RD ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2024, 2024, : 4248 - 4252
  • [9] Knowledge Base Embeddings for a Recommendation Based on Overlapping Knowledge and Graph Learning
    Zhao, Yao
    Wang, Ting
    ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2024,
  • [10] Knowledge graph entity typing via learning connecting embeddings
    Zhao, Yu
    Zhang, Anxiang
    Feng, Huali
    Li, Qing
    Gallinari, Patrick
    Ren, Fuji
    KNOWLEDGE-BASED SYSTEMS, 2020, 196 (196)