Adaptive Loss Weighting via Dynamic Scheduling for Unsupervised Community Detection in Attributed Networks
Mathematics · 28.05.2026 · 14 (11) · 1871
DOI: 10.3390/math14111871 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 28.05.2026. Verfasst von Ying Xu und 2 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Foundation Strengthening Action Plan of Guangxi Basic Research Program.
Abstract (Originalsprache)
Graph Neural Networks (GNNs) have achieved remarkable progress in community detection, which is an essential topic in network analysis with the aim of dividing a network into multiple subgraphs to mine potential information. However, most existing GNN-based community detection approaches adopt static loss function weights during the training process. In this paper, we propose an unsupervised end-to-end community detection framework and define an adaptive loss weighting layer within this framework, named QALW, which is capable of learning an optimal combination of loss weights during model training to balance reconstruction loss and clustering loss. Experimental results obtained based on three real-world benchmark datasets (Cora, Citeseer, and Pubmed) demonstrate that QALW achieves effective and stable community detection performance compared with eight representative baseline methods. In particular, QALW improves ACC by 5.7% over the strongest baseline on the Cora dataset, and achieves ACC values of 64.9%, 61.7%, and 63.9% on Cora, Citeseer, and Pubmed, respectively. Furthermore, the results verify that the proposed dynamic scheduling mechanism effectively alleviates gradient conflicts and enables more stable optimization than fixed-weight strategies. Overall, QALW demonstrates promising competitiveness and good robustness for unsupervised community detection in attributed networks.
Förderung
- National Natural Science Foundation of China
- Foundation Strengthening Action Plan of Guangxi Basic Research Program
Zitieren
APA
Xu, Y., Wu, G., & Hua, L. (2026). Adaptive Loss Weighting via Dynamic Scheduling for Unsupervised Community Detection in Attributed Networks. Mathematics, 14(11), 1871. https://doi.org/10.3390/math14111871
Vancouver
Xu Y, Wu G, Hua L. Adaptive Loss Weighting via Dynamic Scheduling for Unsupervised Community Detection in Attributed Networks. Mathematics. 2026;14(11):1871. doi:10.3390/math14111871
BibTeX
@article{Xu2026,
author = {Xu, Ying and Wu, Guolin and Hua, Liyan},
title = {Adaptive Loss Weighting via Dynamic Scheduling for Unsupervised Community Detection in Attributed Networks},
journal = {Mathematics},
year = {2026},
volume = {14},
number = {11},
pages = {1871},
doi = {10.3390/math14111871}
}
EUVIMED