EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Graph Representation Learning and Its Applications: A Survey

Van Thuy Hoang iD, Hyeon-Ju Jeon iD, Eun-Soon You, Yoewon Yoon iD, Sungyeop Jung iD, O-Joun Lee iD

Sensors · 21.04.2023 · 23 (8) · 4168

DOI: 10.3390/s23084168 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 21.04.2023. Verfasst von Van Thuy Hoang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Artificial Intelligence, The Catholic University of Korea, 43, Jibong-ro, Bucheon-si 14662, Gyeonggi-do, Republic of Korea. Die Arbeit wurde bisher 62-mal zitiert (Crossref) und nennt 441 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Korea Meteorological Administration, Advanced Institute of Convergence Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models.

Schlagwörter

Stichwörter der Autor:innen

graph embeddinggraph neural networksgraph representation learninggraph transformer

Autor:innen und Institutionen

  • Department of Artificial Intelligence, The Catholic University of Korea, 43, Jibong-ro, Bucheon-si 14662, Gyeonggi-do, Republic of Korea.
  • Data Assimilation Group, Korea Institute of Atmospheric Prediction Systems (KIAPS), 35, Boramae-ro 5-gil, Dongjak-gu, Seoul 07071, Republic of Korea.
  • Department of Social Welfare, Dongguk University, 30, Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of Korea.
  • Semiconductor Devices and Circuits Laboratory, Advanced Institute of Convergence Technology (AICT), Seoul National University, 145, Gwanggyo-ro, Yeongtong-gu, Suwon-si 16229, Gyeonggi-do, Republic of Korea.

ORCID-Profile: Van Thuy Hoang, Hyeon-Ju Jeon, Yoewon Yoon, Sungyeop Jung, O-Joun Lee

Förderung

  • National Research Foundation of Korea
  • Korea Meteorological Administration
  • Advanced Institute of Convergence Technology
  • The Catholic University of Korea
  • Korea government (MSIT)

Zitieren

APA

Hoang, V. T., Jeon, H. J., You, E. S., Yoon, Y., Jung, S., & Lee, O. J. (2023). Graph Representation Learning and Its Applications: A Survey. Sensors, 23(8), 4168. https://doi.org/10.3390/s23084168

Vancouver

Hoang VT, Jeon HJ, You ES, Yoon Y, Jung S, Lee OJ. Graph Representation Learning and Its Applications: A Survey. Sensors. 2023;23(8):4168. doi:10.3390/s23084168

BibTeX
@article{Hoang2023,
  author = {Hoang, Van Thuy and Jeon, Hyeon-Ju and You, Eun-Soon and Yoon, Yoewon and Jung, Sungyeop and Lee, O-Joun},
  title = {Graph Representation Learning and Its Applications: A Survey},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {8},
  pages = {4168},
  doi = {10.3390/s23084168}
}
Kostenlos starten →