Introduction to Graph Neural Networks for Machine Learning Engineers
ACM Computing Surveys · 31.10.2026 · 58 (13) · 1-37
DOI: 10.1145/3816725 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 24.06.2026. Verfasst von James Tanis und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 148 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: The MITRE Corporation Independent Research and Development Program.
Abstract (Originalsprache)
Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges. The number of research papers in the literature concerning these models is growing rapidly due to their impressive performance on a broad range of tasks. This survey introduces graph neural networks through the encoder-decoder framework and provides examples of decoders for a range of graph analytic tasks. It uses theory and numerous experiments on homogeneous graphs to illustrate the behavior of graph neural networks under different training sizes and degrees of graph complexity, with an emphasis on oversmoothing and oversquashing.
Förderung
- The MITRE Corporation Independent Research and Development Program
Zitieren
APA
Tanis, J., Giannella, C., Mariano, A., & Meerzaman, D. (2026). Introduction to Graph Neural Networks for Machine Learning Engineers. ACM Computing Surveys, 58(13), 1-37. https://doi.org/10.1145/3816725
Vancouver
Tanis J, Giannella C, Mariano A, Meerzaman D. Introduction to Graph Neural Networks for Machine Learning Engineers. ACM Computing Surveys. 2026;58(13):1-37. doi:10.1145/3816725
BibTeX
@article{Tanis2026,
author = {Tanis, James and Giannella, Chris and Mariano, Adrian and Meerzaman, Daoud},
title = {Introduction to Graph Neural Networks for Machine Learning Engineers},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {13},
pages = {1--37},
doi = {10.1145/3816725}
}
EUVIMED