GEval: A Modular and Extensible Evaluation Framework for Graph Embedding Techniques. Pellegrino, M. A., Altabba, A., Garofalo, M., Ristoski, P., & Cochez, M. In Harth, A., Kirrane, S., Ngonga Ngomo, A., Paulheim, H., Rula, A., Gentile, A. L., Haase, P., & Cochez, M., editors, The Semantic Web, pages 565–582, Cham, 2020. Springer International Publishing.
abstract   bibtex   
While RDF data are graph shaped by nature, most traditional Machine Learning (ML) algorithms expect data in a vector form. To transform graph elements to vectors, several graph embedding approaches have been proposed. Comparing these approaches is interesting for 1) developers of new embedding techniques to verify in which cases their proposal outperforms the state-of-art and 2) consumers of these techniques in choosing the best approach according to the task(s) the vectors will be used for. The comparison could be delayed (and made difficult) by the choice of tasks, the design of the evaluation, the selection of models, parameters, and needed datasets. We propose GEval, an evaluation framework to simplify the evaluation and the comparison of graph embedding techniques. The covered tasks range from ML tasks (Classification, Regression, Clustering), semantic tasks (entity relatedness, document similarity) to semantic analogies. However, GEval is designed to be (easily) extensible. In this article, we will describe the design and development of the proposed framework by detailing its overall structure, the already implemented tasks, and how to extend it. In conclusion, to demonstrate its operating approach, we consider the parameter tuning of the KGloVe algorithm as a use case.
@inproceedings{pellegrino_geval_2020,
	address = {Cham},
	title = {{GEval}: {A} {Modular} and {Extensible} {Evaluation} {Framework} for {Graph} {Embedding} {Techniques}},
	isbn = {978-3-030-49461-2},
	abstract = {While RDF data are graph shaped by nature, most traditional Machine Learning (ML) algorithms expect data in a vector form. To transform graph elements to vectors, several graph embedding approaches have been proposed. Comparing these approaches is interesting for 1) developers of new embedding techniques to verify in which cases their proposal outperforms the state-of-art and 2) consumers of these techniques in choosing the best approach according to the task(s) the vectors will be used for. The comparison could be delayed (and made difficult) by the choice of tasks, the design of the evaluation, the selection of models, parameters, and needed datasets. We propose GEval, an evaluation framework to simplify the evaluation and the comparison of graph embedding techniques. The covered tasks range from ML tasks (Classification, Regression, Clustering), semantic tasks (entity relatedness, document similarity) to semantic analogies. However, GEval is designed to be (easily) extensible. In this article, we will describe the design and development of the proposed framework by detailing its overall structure, the already implemented tasks, and how to extend it. In conclusion, to demonstrate its operating approach, we consider the parameter tuning of the KGloVe algorithm as a use case.},
	booktitle = {The {Semantic} {Web}},
	publisher = {Springer International Publishing},
	author = {Pellegrino, Maria Angela and Altabba, Abdulrahman and Garofalo, Martina and Ristoski, Petar and Cochez, Michael},
	editor = {Harth, Andreas and Kirrane, Sabrina and Ngonga Ngomo, Axel-Cyrille and Paulheim, Heiko and Rula, Anisa and Gentile, Anna Lisa and Haase, Peter and Cochez, Michael},
	year = {2020},
	pages = {565--582},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021