Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 1.62 MB
Add to list
  1. Search results
  2. An empirical evaluation of network re...

An empirical evaluation of network representation learning methods

Alexandru-Cristian Mara (UGent) , Jefrey Lijffijt (UGent) and Tijl De Bie (UGent)
(2023) BIG DATA.
Author
Organization
Project
Abstract
Network representation learning methods map network nodes to vectors in an embedding space that can preserve specific properties and enable traditional downstream prediction tasks. The quality of the representations learned is then generally showcased through results on these downstream tasks. Commonly used benchmark tasks such as link prediction or network reconstruction, however, present complex evaluation pipelines and an abundance of design choices. This, together with a lack of standardized evaluation setups, can obscure the real progress in the field. In this article, we aim at investigating the impact on the performance of a variety of such design choices and perform an extensive and consistent evaluation that can shed light on the state-of-the-art on network representation learning. Our evaluation reveals that only limited progress has been made in recent years, with embedding-based approaches struggling to outperform basic heuristics in many scenarios.
Keywords
representation learning, network embedding, benchmark, evaluation, network reconstruction, link prediction

Downloads

  • Download
    DS502.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.62 MB

Citation

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

MLA
Mara, Alexandru-Cristian, et al. “An Empirical Evaluation of Network Representation Learning Methods.” BIG DATA, 2023, doi:10.1089/big.2021.0107.
APA
Mara, A.-C., Lijffijt, J., & De Bie, T. (2023). An empirical evaluation of network representation learning methods. BIG DATA. https://doi.org/10.1089/big.2021.0107
Chicago author-date
Mara, Alexandru-Cristian, Jefrey Lijffijt, and Tijl De Bie. 2023. “An Empirical Evaluation of Network Representation Learning Methods.” BIG DATA. https://doi.org/10.1089/big.2021.0107.
Chicago author-date (all authors)
Mara, Alexandru-Cristian, Jefrey Lijffijt, and Tijl De Bie. 2023. “An Empirical Evaluation of Network Representation Learning Methods.” BIG DATA. doi:10.1089/big.2021.0107.
Vancouver
1.
Mara A-C, Lijffijt J, De Bie T. An empirical evaluation of network representation learning methods. BIG DATA. 2023;
IEEE
[1]
A.-C. Mara, J. Lijffijt, and T. De Bie, “An empirical evaluation of network representation learning methods,” BIG DATA, 2023.
@article{8748224,
  abstract     = {{Network representation learning methods map network nodes to vectors in an embedding space that can preserve specific properties and enable traditional downstream prediction tasks. The quality of the representations learned is then generally showcased through results on these downstream tasks. Commonly used benchmark tasks such as link prediction or network reconstruction, however, present complex evaluation pipelines and an abundance of design choices. This, together with a lack of standardized evaluation setups, can obscure the real progress in the field. In this article, we aim at investigating the impact on the performance of a variety of such design choices and perform an extensive and consistent evaluation that can shed light on the state-of-the-art on network representation learning. Our evaluation reveals that only limited progress has been made in recent years, with embedding-based approaches struggling to outperform basic heuristics in many scenarios.}},
  author       = {{Mara, Alexandru-Cristian and Lijffijt, Jefrey and De Bie, Tijl}},
  issn         = {{2167-6461}},
  journal      = {{BIG DATA}},
  keywords     = {{representation learning,network embedding,benchmark,evaluation,network reconstruction,link prediction}},
  language     = {{eng}},
  pages        = {{20}},
  title        = {{An empirical evaluation of network representation learning methods}},
  url          = {{http://doi.org/10.1089/big.2021.0107}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: