Representation learning for knowledge fusion and reasoning in Cyber-Physical-Social Systems: Survey and perspectives

被引:10
作者
Yang, Jing [1 ]
Yang, Laurence T. [1 ,2 ]
Wang, Hao [3 ]
Gao, Yuan [1 ]
Zhao, Yaliang [4 ]
Xie, Xia [1 ]
Lu, Yan [1 ]
机构
[1] Hainan Univ, Haikou 570000, Peoples R China
[2] St Francis Xavier Univ, Antigonish, NS B2G 2W5, Canada
[3] Huazhong Univ Sci & Technol, Wuhan 430074, Peoples R China
[4] Henan Univ, Kaifeng 475001, Peoples R China
基金
中国国家自然科学基金;
关键词
Cyber-Physical-Social Systems; Knowledge graph; Knowledge fusion; Knowledge reasoning; Representation learning; Knowledge graph embedding; Graph neural networks; Tensor; NEURAL-NETWORKS; MODEL;
D O I
10.1016/j.inffus.2022.09.003
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The digital deep integration of cyber space, physical space and social space facilitates the formation of Cyber-Physical-Social Systems (CPSS). Knowledge empowers CPSS to be capable of solving complex tasks and providing intelligent services. Knowledge representation, fusion, and reasoning are complementary in the knowledge graph and worthy of continuous exploration and in-depth research. Since the concept of knowledge representation learning has been proposed, various models have been developed and demonstrated their superior ability in knowledge fusion and reasoning. In this paper, we investigate the progress and function of representation learning models adopted in knowledge fusion and reasoning, and extract their commonalities and characteristics, which is a perspective that has never been developed before, to provide new ideas for scholars and realize the mutual promotion of knowledge fusion and reasoning. This paper comprehensively reviews classic methods and investigates advanced and emerging works, which are published in authoritative journals or conferences. Furthermore, to overcome the limitations of existing methods, we propose an integrated knowledge representation learning and application framework for CPSS and a series of tensor-based knowledge fusion and reasoning models. Finally, four future directions are discussed in this paper, we analyze the challenges faced by them and suggest promising solutions.
引用
收藏
页码:59 / 73
页数:15
相关论文
共 147 条
[1]   Hypernetwork Knowledge Graph Embeddings [J].
Balazevic, Ivana ;
Allen, Carl ;
Hospedales, Timothy M. .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: WORKSHOP AND SPECIAL SESSIONS, 2019, 11731 :553-565
[2]  
Bauer L, 2018, 2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), P4220
[3]  
Bian T, 2020, AAAI CONF ARTIF INTE, V34, P549
[4]  
Bordes A., 2011, P 25 AAAI C ART INT, P301
[5]  
Bordes A, 2015, Arxiv, DOI arXiv:1506.02075
[6]   A semantic matching energy function for learning with multi-relational data Application to word-sense disambiguation [J].
Bordes, Antoine ;
Glorot, Xavier ;
Weston, Jason ;
Bengio, Yoshua .
MACHINE LEARNING, 2014, 94 (02) :233-259
[7]  
Bordes Antoine, 2013, PROCADV NEURAL INF P, V26
[8]  
Bruna J, 2014, P 2 INT C LEARN REPR, DOI DOI 10.48550/ARXIV.1312.6203
[9]   TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction [J].
Cai, Ling ;
Yan, Bo ;
Mai, Gengchen ;
Janowicz, Krzysztof ;
Zhu, Rui .
PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON KNOWLEDGE CAPTURE (K-CAP '19), 2019, :131-138
[10]  
Cao SS, 2016, AAAI CONF ARTIF INTE, P1145