EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Unsupervised Graph Representation Learning with Inductive Shallow Node Embedding

Richárd Kiss, Gábor Szűcs

Complex & Intelligent Systems · 2024-10 · 10 (5) · 7333-7348

DOI: 10.1007/s40747-024-01545-6 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 12.07.2024. Verfasst von Richárd Kiss und 1 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Budapest University of Technology and Economics.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Network science has witnessed a surge in popularity, driven by the transformative power of node representation learning for diverse applications like social network analysis and biological modeling. While shallow embedding algorithms excel at capturing network structure, they face a critical limitation—failing to generalize to unseen nodes. This paper addresses this challenge by introducing Inductive Shallow Node Embedding—as a main contribution—pioneering a novel approach that extends shallow embeddings to the realm of inductive learning. It has a novel encoder architecture that captures the local neighborhood structure of each node, enabling effective generalization to unseen nodes. In the generalization, robustness is essential to avoid degradation of performance arising from noise in the dataset. It has been theoretically proven that the covariance of the additive noise term in the proposed model is inversely proportional to the cardinality of a node’s neighbors. Another contribution is a mathematical lower bound to quantify the robustness of node embeddings, confirming its advantage over traditional shallow embedding methods, particularly in the presence of parameter noise. The proposed method demonstrably excels in dynamic networks, consistently achieving over 90% performance on previously unseen nodes compared to nodes encountered during training on various benchmarks. The empirical evaluation concludes that our method outperforms competing methods on the vast majority of datasets in both transductive and inductive tasks.

Förderung

  • Budapest University of Technology and Economics

Zitieren

APA

Kiss, R., & Szűcs, G. (2024). Unsupervised Graph Representation Learning with Inductive Shallow Node Embedding. Complex & Intelligent Systems, 10(5), 7333-7348. https://doi.org/10.1007/s40747-024-01545-6

Vancouver

Kiss R, Szűcs G. Unsupervised Graph Representation Learning with Inductive Shallow Node Embedding. Complex & Intelligent Systems. 2024;10(5):7333-7348. doi:10.1007/s40747-024-01545-6

BibTeX
@article{Kiss2024,
  author = {Kiss, Richárd and Szűcs, Gábor},
  title = {Unsupervised Graph Representation Learning with Inductive Shallow Node Embedding},
  journal = {Complex & Intelligent Systems},
  year = {2024},
  volume = {10},
  number = {5},
  pages = {7333--7348},
  doi = {10.1007/s40747-024-01545-6}
}
Kostenlos starten →