EUVIMEDEUVIMED entdecken
Crossref

State of the Art and Potentialities of Graph-level Learning

Zhenyu Yang, Ge Zhang, Jia Wu, Jian Yang, Quan Z. Sheng, Shan Xue, Chuan Zhou, Charu Aggarwal, Hao Peng, Wenbin Hu, Edwin Hancock, Pietro Liò

ACM Computing Surveys · 28.02.2025 · 57 (2) · 1-40

DOI: 10.1145/3695863 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.10.2024. Verfasst von Zhenyu Yang und 11 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 220 Literaturangaben. Gefördert von: Australian Research Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graphs have a superior ability to represent relational data, such as chemical compounds, proteins, and social networks. Hence, graph-level learning, which takes a set of graphs as input, has been applied to many tasks, including comparison, regression, classification, and more. Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures. While these methods benefit from good interpretability, they often suffer from computational bottlenecks, as they cannot skirt the graph isomorphism problem. Conversely, deep learning has helped graph-level learning adapt to the growing scale of graphs by extracting features automatically and encoding graphs into low-dimensional representations. As a result, these deep graph learning methods have been responsible for many successes. Yet, no comprehensive survey reviews graph-level learning starting with traditional learning and moving through to the deep learning approaches. This article fills this gap and frames the representative algorithms into a systematic taxonomy covering traditional learning, graph-level deep neural networks, graph-level graph neural networks, and graph pooling. In addition, the evolution and interaction between methods from these four branches within their developments are examined to provide an in-depth analysis. This is followed by a brief review of the benchmark datasets, evaluation metrics, and common downstream applications. Finally, the survey concludes with an in-depth discussion of 12 current and future directions in this booming field.

Förderung

  • Australian Research Council

Zitieren

APA

Yang, Z., Zhang, G., Wu, J., Yang, J., Sheng, Q. Z., Xue, S., Zhou, C., Aggarwal, C., Peng, H., Hu, W., Hancock, E., & Liò, P. (2025). State of the Art and Potentialities of Graph-level Learning. ACM Computing Surveys, 57(2), 1-40. https://doi.org/10.1145/3695863

Vancouver

Yang Z, Zhang G, Wu J, Yang J, Sheng QZ, Xue S, et al. State of the Art and Potentialities of Graph-level Learning. ACM Computing Surveys. 2025;57(2):1-40. doi:10.1145/3695863

BibTeX
@article{Yang2025,
  author = {Yang, Zhenyu and Zhang, Ge and Wu, Jia and Yang, Jian and Sheng, Quan Z. and Xue, Shan and Zhou, Chuan and Aggarwal, Charu and Peng, Hao and Hu, Wenbin and Hancock, Edwin and Liò, Pietro},
  title = {State of the Art and Potentialities of Graph-level Learning},
  journal = {ACM Computing Surveys},
  year = {2025},
  volume = {57},
  number = {2},
  pages = {1--40},
  doi = {10.1145/3695863}
}
Kostenlos starten →