EUVIMEDEUVIMED entdecken
Crossref

Trustworthy Neighborhoods Mining: Homophily-Aware Neutral Contrastive Learning for Graph Clustering

Liang Peng, Yixuan Ye, Cheng Liu, Hangjun Che, Man-Fai Leung, Si Wu, Hau-San Wong

IEEE Transactions on Knowledge and Data Engineering · 2026-01 · 38 (1) · 679-693

DOI: 10.1109/tkde.2025.3622998 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-01. Verfasst von Liang Peng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 72 Literaturangaben. Gefördert von: Basic and Applied Basic Research Foundation of Guangdong Province, Fundamental Research Funds for the Central Universities, TCL Science and Technology Innovation Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Basic and Applied Basic Research Foundation of Guangdong Province
  • Fundamental Research Funds for the Central Universities
  • TCL Science and Technology Innovation Fund
  • Research Grants Council of the Hong Kong Special Administration Region

Zitieren

APA

Peng, L., Ye, Y., Liu, C., Che, H., Leung, M., Wu, S., & Wong, H. (2026). Trustworthy Neighborhoods Mining: Homophily-Aware Neutral Contrastive Learning for Graph Clustering. IEEE Transactions on Knowledge and Data Engineering, 38(1), 679-693. https://doi.org/10.1109/tkde.2025.3622998

Vancouver

Peng L, Ye Y, Liu C, Che H, Leung M, Wu S, et al. Trustworthy Neighborhoods Mining: Homophily-Aware Neutral Contrastive Learning for Graph Clustering. IEEE Transactions on Knowledge and Data Engineering. 2026;38(1):679-693. doi:10.1109/tkde.2025.3622998

BibTeX
@article{Peng2026,
  author = {Peng, Liang and Ye, Yixuan and Liu, Cheng and Che, Hangjun and Leung, Man-Fai and Wu, Si and Wong, Hau-San},
  title = {Trustworthy Neighborhoods Mining: Homophily-Aware Neutral Contrastive Learning for Graph Clustering},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {1},
  pages = {679--693},
  doi = {10.1109/tkde.2025.3622998}
}
Kostenlos starten →