EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GCR-Net: Stable Reinforcement Learning for Community Detection with Unknown Community Count in Attributed Networks

Wencai He, Zhijie Peng, Yuanbin He, Ziyu Zhang, Mingshen Zhang, He Zhu

Algorithms · 16.06.2026 · 19 (6) · 484

DOI: 10.3390/a19060484 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 16.06.2026. Verfasst von Wencai He und 5 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Community detection in attributed networks becomes considerably more challenging when the number of communities is unknown in advance. Most existing deep community detection methods assume a fixed community count, whereas reinforcement learning (RL)-based alternatives often suffer from overestimated action values and unstable target updates. To address these limitations, we propose GCR-Net (Graph Community Recognition Network), an RL-guided framework that combines representation learning with adaptive community-count selection. The method adapts decoupled value estimation and gradual anchor-network updates from established deep RL techniques to a formal MDP over candidate community counts. Experiments on citation, social, biomedical, and proteininteraction benchmarks, together with synthetic graphs with more than ten communities, show that GCR-Net delivers competitive NMI and ARI scores with lower variance and more stable optimization than conventional RL baselines. Statistical tests indicate that the clearest gains concern training stability rather than large accuracy margins.

Zitieren

APA

He, W., Peng, Z., He, Y., Zhang, Z., Zhang, M., & Zhu, H. (2026). GCR-Net: Stable Reinforcement Learning for Community Detection with Unknown Community Count in Attributed Networks. Algorithms, 19(6), 484. https://doi.org/10.3390/a19060484

Vancouver

He W, Peng Z, He Y, Zhang Z, Zhang M, Zhu H. GCR-Net: Stable Reinforcement Learning for Community Detection with Unknown Community Count in Attributed Networks. Algorithms. 2026;19(6):484. doi:10.3390/a19060484

BibTeX
@article{He2026,
  author = {He, Wencai and Peng, Zhijie and He, Yuanbin and Zhang, Ziyu and Zhang, Mingshen and Zhu, He},
  title = {GCR-Net: Stable Reinforcement Learning for Community Detection with Unknown Community Count in Attributed Networks},
  journal = {Algorithms},
  year = {2026},
  volume = {19},
  number = {6},
  pages = {484},
  doi = {10.3390/a19060484}
}
Kostenlos starten →