Advanced search
1 file | 305.75 KB Add to list

EvalNE : a framework for network embedding evaluation

Alexandru-Cristian Mara (UGent) , Jefrey Lijffijt (UGent) and Tijl De Bie (UGent)
(2022) SOFTWAREX. 17.
Author
Organization
Project
Abstract
In this paper we introduce EvalNE, a Python toolbox for network embedding evaluation. The main goal of EvalNE is to aid researchers and practitioners in performing consistent and reproducible evaluations of new embedding methods, replicating existing evaluations, and conducting benchmark studies. The toolbox can evaluate models independently of their programming language and assess the quality of learned representations through data visualization and downstream tasks such as sign and link prediction, network reconstruction, and node multi-label classification. EvalNE streamlines evaluation by providing automation and abstraction for tasks such as hyperparameter tuning and model validation, node and edge sampling, node-pair embedding computation, and performance reporting. As a command line tool, configuration files describe the evaluation setup and guarantee consistency and reproducibility. As an API, EvalNE provides the building blocks to design any evaluation setup while minimizing the risk of evaluation errors. (C) 2022 The Author(s). Published by Elsevier B.V.
Keywords
Computer Science Applications, Software, Representation learning, Evaluation, Reproducibility, Open-source tools

Downloads

  • 1-s2.0-S2352711022000139-main.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 305.75 KB

Citation

Please use this url to cite or link to this publication:

MLA
Mara, Alexandru-Cristian, et al. “EvalNE : A Framework for Network Embedding Evaluation.” SOFTWAREX, vol. 17, 2022, doi:10.1016/j.softx.2022.100997.
APA
Mara, A.-C., Lijffijt, J., & De Bie, T. (2022). EvalNE : a framework for network embedding evaluation. SOFTWAREX, 17. https://doi.org/10.1016/j.softx.2022.100997
Chicago author-date
Mara, Alexandru-Cristian, Jefrey Lijffijt, and Tijl De Bie. 2022. “EvalNE : A Framework for Network Embedding Evaluation.” SOFTWAREX 17. https://doi.org/10.1016/j.softx.2022.100997.
Chicago author-date (all authors)
Mara, Alexandru-Cristian, Jefrey Lijffijt, and Tijl De Bie. 2022. “EvalNE : A Framework for Network Embedding Evaluation.” SOFTWAREX 17. doi:10.1016/j.softx.2022.100997.
Vancouver
1.
Mara A-C, Lijffijt J, De Bie T. EvalNE : a framework for network embedding evaluation. SOFTWAREX. 2022;17.
IEEE
[1]
A.-C. Mara, J. Lijffijt, and T. De Bie, “EvalNE : a framework for network embedding evaluation,” SOFTWAREX, vol. 17, 2022.
@article{8738277,
  abstract     = {{In this paper we introduce EvalNE, a Python toolbox for network embedding evaluation. The main goal of EvalNE is to aid researchers and practitioners in performing consistent and reproducible evaluations of new embedding methods, replicating existing evaluations, and conducting benchmark studies. The toolbox can evaluate models independently of their programming language and assess the quality of learned representations through data visualization and downstream tasks such as sign and link prediction, network reconstruction, and node multi-label classification. EvalNE streamlines evaluation by providing automation and abstraction for tasks such as hyperparameter tuning and model validation, node and edge sampling, node-pair embedding computation, and performance reporting. As a command line tool, configuration files describe the evaluation setup and guarantee consistency and reproducibility. As an API, EvalNE provides the building blocks to design any evaluation setup while minimizing the risk of evaluation errors. (C) 2022 The Author(s). Published by Elsevier B.V.}},
  articleno    = {{100997}},
  author       = {{Mara, Alexandru-Cristian and Lijffijt, Jefrey and De Bie, Tijl}},
  issn         = {{2352-7110}},
  journal      = {{SOFTWAREX}},
  keywords     = {{Computer Science Applications,Software,Representation learning,Evaluation,Reproducibility,Open-source tools}},
  language     = {{eng}},
  pages        = {{4}},
  title        = {{EvalNE : a framework for network embedding evaluation}},
  url          = {{http://dx.doi.org/10.1016/j.softx.2022.100997}},
  volume       = {{17}},
  year         = {{2022}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: