EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CasDacGCN: A Dynamic Attention-Calibrated Graph Convolutional Network for Information Popularity Prediction

Bofeng Zhang iD, Yanlin Zhu, Zhirong Zhang, Kaili Liao, Sen Niu iD, Bingchun Li, Haiyan Li

Entropy · 14.10.2025 · 27 (10) · 1064

DOI: 10.3390/e27101064 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 14.10.2025. Verfasst von Bofeng Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Kashi University, Kashi 844000, China. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Fundamental Research Funds for the Xinjing University, Shanghai Central Guide Local Science and Technology Development Fund Projects, Natural Science Foundation of Xinjiang.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Information popularity prediction is a critical problem in social network analysis. With the increasing prevalence of social platforms, accurate prediction of the diffusion process has become increasingly important. Existing methods mainly rely on graph neural networks to model structural relationships, but they are often insufficient in capturing the complex interplay between temporal evolution and local cascade structures, especially in real-world scenarios involving sparse or rapidly changing cascades. To address this issue, we propose the Cascading Dynamic attention-calibrated Graph Convolutional Network, named CasDacGCN. It enhances prediction performance through spatiotemporal feature fusion and adaptive representation learning. The model integrates snapshot-level local encoding, global temporal modeling, cross-attention mechanisms, and a hypernetwork-based sample-wise calibration strategy, enabling flexible modeling of multi-scale diffusion patterns. Results from experiments demonstrate that the proposed model consistently surpasses existing approaches on two real-world datasets, validating its effectiveness in popularity prediction tasks.

Schlagwörter

Stichwörter der Autor:innen

graph convolutional networkinformation diffusioninformation popularity predictiontemporal graph

Autor:innen und Institutionen

  • School of Computer Science and Technology, Kashi University, Kashi 844000, China.
  • School of Computer and Information Engineering, Institute for Artificial Intelligence, Shanghai Polytechnic University, Shanghai 201209, China.

ORCID-Profile: Bofeng Zhang, Sen Niu

Förderung

  • the Fundamental Research Funds for the Xinjing University
  • Shanghai Central Guide Local Science and Technology Development Fund Projects
  • Natural Science Foundation of Xinjiang
  • Shanghai Central Guide Local Science
  • Natural Science Foundation of Xinjiang Uygur Autonomous Region

Zitieren

APA

Zhang, B., Zhu, Y., Zhang, Z., Liao, K., Niu, S., Li, B., & Li, H. (2025). CasDacGCN: A Dynamic Attention-Calibrated Graph Convolutional Network for Information Popularity Prediction. Entropy, 27(10), 1064. https://doi.org/10.3390/e27101064

Vancouver

Zhang B, Zhu Y, Zhang Z, Liao K, Niu S, Li B, et al. CasDacGCN: A Dynamic Attention-Calibrated Graph Convolutional Network for Information Popularity Prediction. Entropy. 2025;27(10):1064. doi:10.3390/e27101064

BibTeX
@article{Zhang2025,
  author = {Zhang, Bofeng and Zhu, Yanlin and Zhang, Zhirong and Liao, Kaili and Niu, Sen and Li, Bingchun and Li, Haiyan},
  title = {CasDacGCN: A Dynamic Attention-Calibrated Graph Convolutional Network for Information Popularity Prediction},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {10},
  pages = {1064},
  doi = {10.3390/e27101064}
}
Kostenlos starten →