A4 Article in conference proceedings
A Configurable Evaluation Framework for Node Embedding Techniques (2019)


Pellegrino, Maria Angela; Cochez, Michael; Garofalo, Martina; Ristoski, Petar (2019). A Configurable Evaluation Framework for Node Embedding Techniques. In Hitzler, Pascal; Kirrane, Sabrina; Hartig, Olaf; de Boer, Victor; Vidal, Maria-Esther; Maleshkova, Maria; Schlobach, Stefan; Hammar, Karl; Lasierra, Nelia; Stadtmüller, Steffen; Hose, Katja et al. (Eds.) The Semantic Web : ESWC 2019 Satellite Events, Revised Selected Papers, Lecture Notes in Computer Science, 11762. Cham: Springer, 156-160. DOI: 10.1007/978-3-030-32327-1_31


JYU authors or editors


Publication details

All authors or editors: Pellegrino, Maria Angela; Cochez, Michael; Garofalo, Martina; Ristoski, Petar

Parent publication: The Semantic Web : ESWC 2019 Satellite Events, Revised Selected Papers

Parent publication editors: Hitzler, Pascal; Kirrane, Sabrina; Hartig, Olaf; de Boer, Victor; Vidal, Maria-Esther; Maleshkova, Maria; Schlobach, Stefan; Hammar, Karl; Lasierra, Nelia; Stadtmüller, Steffen; Hose, Katja; Verborgh, Rube

Conference:

European Semantic Web Conference

Place and date of conference: Portorož, Slovenia, 2.6.6.2019

ISBN: 978-3-030-32326-4

eISBN: 978-3-030-32327-1

Journal or series: Lecture Notes in Computer Science

ISSN: 0302-9743

eISSN: 1611-3349

Publication year: 2019

Number in series: 11762

Pages range: 156-160

Number of pages in the book: 302

Publisher: Springer

Place of Publication: Cham

Publication country: Switzerland

Publication language: English

DOI: http://doi.org/10.1007/978-3-030-32327-1_31

Open Access: Publication channel is not openly available


Abstract

While Knowledge Graphs (KG) are graph shaped by nature, most traditional data mining and machine learning (ML) software expect data in a vector form. Several node embedding techniques have been proposed to represent each node in the KG as a low-dimensional feature vector. A node embedding technique should preferably be task independent. Therefore, when a new method has been developed, it should be tested on the tasks it was designed for as well as on other tasks. We present the design and implementation of a ready to use evaluation framework to simplify the node embedding technique testing phase. The provided tests range from ML tasks, semantic tasks to semantic analogies.


Keywords: data mining; machine learning; semantic web

Free keywords: evaluation framework; node embedding; machine learning; semantic tasks


Contributing organizations


Ministry reporting: Yes

Reporting Year: 2019

JUFO rating: 1


Last updated on 2020-09-07 at 11:55