EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating a Sequential Model Into GNN-Based Social Recommendation for Relieving Over-Smoothing Problem

Janekhwan Kitsupapaisan, Saranya Maneeroj, Atsuhiro Takasu

IEEE Access · 2025 · 13 · 100219-100233

DOI: 10.1109/access.2025.3574781 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2025. Verfasst von Janekhwan Kitsupapaisan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, social recommendation systems have increasingly integrated Graph Neural Networks (GNNs) to capture social relationships among users from both direct and higher-order neighbors. However, these state-of-the-art models face limitations regarding the number of iterations they can propagate across the graph. Messages from higher-order neighbors often dilute the unique characteristics of the target node. This causes node representations to become similar and indistinguishable, leading to a phenomenon known as the over-smoothing problem. Several works have attempted to address this problem with the expectation of preserving user characteristics. They add auxiliary information to the GNN-based social recommendation models without considering the dynamic preferences of users, which frequently change over time. Therefore, those works still struggle with the same problem after propagating in a few iterations. To mitigate this phenomenon, we propose a novel approach to integrate user characteristics extracted from users’ historical interactions using a sequential model to slow down node convergence. Integrating user characteristics into the GNN-based social recommendation will allow the model to capture user preferences that dynamically change over time. Consequently, the proposed model will be able to leverage informative data from higher-order neighbors over social networks for user representation learning, leading to better performance and effectiveness of the recommendations. Our experimental results demonstrate that the proposed model outperforms state-of-the-art social recommendation models across three benchmark datasets.

Zitieren

APA

Kitsupapaisan, J., Maneeroj, S., & Takasu, A. (2025). Integrating a Sequential Model Into GNN-Based Social Recommendation for Relieving Over-Smoothing Problem. IEEE Access, 13, 100219-100233. https://doi.org/10.1109/access.2025.3574781

Vancouver

Kitsupapaisan J, Maneeroj S, Takasu A. Integrating a Sequential Model Into GNN-Based Social Recommendation for Relieving Over-Smoothing Problem. IEEE Access. 2025;13:100219-100233. doi:10.1109/access.2025.3574781

BibTeX
@article{Kitsupapaisan2025,
  author = {Kitsupapaisan, Janekhwan and Maneeroj, Saranya and Takasu, Atsuhiro},
  title = {Integrating a Sequential Model Into GNN-Based Social Recommendation for Relieving Over-Smoothing Problem},
  journal = {IEEE Access},
  year = {2025},
  volume = {13},
  pages = {100219--100233},
  doi = {10.1109/access.2025.3574781}
}
Kostenlos starten →