Walk Extraction Strategies for Node Embeddings with RDF2Vec in Knowledge Graphs

被引:8
作者
Steenwinckel, Bram [1 ]
Vandewiele, Gilles [1 ]
Bonte, Pieter [1 ]
Weyns, Michael [1 ]
Paulheim, Heiko [2 ]
Ristoski, Petar [3 ]
De Turck, Filip [1 ]
Ongenae, Femke [1 ]
机构
[1] Univ Ghent, IDLab, Imec, Ghent, Belgium
[2] Univ Mannheim, Data & Web Sci Grp, Mannheim, Germany
[3] eBay Res, San Jose, CA USA
来源
DATABASE AND EXPERT SYSTEMS APPLICATIONS - DEXA 2021 WORKSHOPS | 2021年 / 1479卷
关键词
Knowledge graphs; Embeddings; Representation learning;
D O I
10.1007/978-3-030-87101-7_8
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
As Knowledge Graphs are symbolic constructs, specialized techniques have to be applied in order to make them compatible with data mining techniques. RDF2Vec is an unsupervised technique that can create task-agnostic numerical representations of the nodes in a KG by extending successful language modeling techniques. The original work proposed the Weisfeiler-Lehman kernel to improve the quality of the representations. However, in this work, we show that the Weisfeiler-Lehman kernel does little to improve walk embeddings in the context of a single Knowledge Graph. As an alternative, we examined five alternative strategies to extract information complementary to basic random walks and compare them on several benchmark datasets to show that research within this field is still relevant for node classification tasks.
引用
收藏
页码:70 / 80
页数:11
相关论文
共 29 条
[1]  
[Anonymous], 2014, ARXIV PREPRINT ARXIV
[2]   Fast unfolding of communities in large networks [J].
Blondel, Vincent D. ;
Guillaume, Jean-Loup ;
Lambiotte, Renaud ;
Lefebvre, Etienne .
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2008,
[3]  
Cochez Michael, P 7 INT C WEB INT MI, P1
[4]  
de Vries Gerben K. D., 2013, Machine Learning and Knowledge Discovery in Databases. European Conference, ECML PKDD 2013. Proceedings: LNCS 8188, P606, DOI 10.1007/978-3-642-40988-2_39
[5]   Substructure counting graph kernels for machine learning from RDF data [J].
de Vries, Gerben Klaas Dirk ;
de Rooij, Steven .
JOURNAL OF WEB SEMANTICS, 2015, 35 :71-84
[6]   Community detection in graphs [J].
Fortunato, Santo .
PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS, 2010, 486 (3-5) :75-174
[7]   node2vec: Scalable Feature Learning for Networks [J].
Grover, Aditya ;
Leskovec, Jure .
KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :855-864
[8]  
Hamilton W.L., 2017, IEEE Data Engineering Bulletin
[9]  
Ivanov S., 2018, ARXIV PREPRINT ARXIV
[10]   A survey on graph kernels [J].
Kriege, Nils M. ;
Johansson, Fredrik D. ;
Morris, Christopher .
APPLIED NETWORK SCIENCE, 2020, 5 (01)