EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

PruferNET: An Augmented Graph Neural Network for Influential Node Detection in Social Networks

Atashi Saha, Nayan Kumar Sarkar, Sanjoy Pratihar

IEEE Access · 2026 · 14 · 79940-79959

DOI: 10.1109/access.2026.3695637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Atashi Saha und 2 weiteren Autor:innen. Die Arbeit nennt 87 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Finding influential nodes, or people, on a social network is very important because it supports many important uses in different fields. This paper proposes a new way to classify social media nodes using Prufer sequence-based structural features with Graph Neural Networks (GNNs). Using the Facebook dataset, a Minimum Spanning Tree (MST) is built to generate the Prufer sequence and extract graph-based features. To build a detailed feature set, properties such as label frequency, sequence entropy, subtree depth, unique label ratio, and transition influence are combined with traditional structural measures such as degree centrality, closeness centrality, and PageRank. The method employs a GraphSAGE model for node classification, where nodes are tagged as Very Shallow, Shallow, or Deep according to their relative depth in the reconstructed Prufer tree. The results show that the integration of Prufer-based features significantly improves performance. The method achieved a test precision of 99.63% after adding Prufer features with traditional feature vectors. This is considerably higher than the accuracy 96.54% obtained using only traditional features. The precision, recall, and F1 scores across all categories show the strength and reliability of the proposed method. The results highlight the effectiveness of this combined graph-based representation. The findings demonstrate improved performance, especially for those derived from spanning tree encodings such as Prufer sequences, with deep learning models. This system effectively captures hidden structural patterns and identifies influential nodes in large social graphs.

Zitieren

APA

Saha, A., Sarkar, N. K., & Pratihar, S. (2026). PruferNET: An Augmented Graph Neural Network for Influential Node Detection in Social Networks. IEEE Access, 14, 79940-79959. https://doi.org/10.1109/access.2026.3695637

Vancouver

Saha A, Sarkar NK, Pratihar S. PruferNET: An Augmented Graph Neural Network for Influential Node Detection in Social Networks. IEEE Access. 2026;14:79940-79959. doi:10.1109/access.2026.3695637

BibTeX
@article{Saha2026,
  author = {Saha, Atashi and Sarkar, Nayan Kumar and Pratihar, Sanjoy},
  title = {PruferNET: An Augmented Graph Neural Network for Influential Node Detection in Social Networks},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {79940--79959},
  doi = {10.1109/access.2026.3695637}
}
Kostenlos starten →