EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Parameter-Efficient Personalized Federated Learning for Accurate Cellular Traffic Prediction

Xingyu Tian, Citong Que, Faisal Nadeem Khan

Telecom · 12.08.2026 · 7 (4) · 104

DOI: 10.3390/telecom7040104 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Telecom, online erschienen am 12.08.2026. Verfasst von Xingyu Tian und 2 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Innovative and Entrepreneurial Research Team Program, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables cellular traffic prediction without centralizing raw base-station data, but statistical heterogeneity makes a single global model unsuitable for many clients. This paper proposes federated clustering with adaptive personalization (FedCAP), a parameter-efficient personalized FL framework that separates cluster-level representation learning from client-level adaptation. Clients are grouped using training-only daily traffic profiles, after which an LSTM backbone is trained by FedAvg within each cluster. Each client then freezes the cluster backbone and optimizes a residual bottleneck adapter locally. The adapter contains 4241 trainable parameters, 6.19% of the 68,483-parameter three-feature backbone and prediction head, and personalization transmits no model updates. In a shared-seed-42 comparison across 11 methods and four public datasets, FedCAP ranks first or second in 12 of 16 dataset–metric combinations. Across five shared seeds, its mean MAE is 6.66%, 7.47%, 2.64%, and 3.86% below FedAvg on the Milan, Trentino, Bihar, and Taiwan datasets, respectively. Holm-adjusted paired t-tests identify 6 significant dataset–metric differences, whereas exact Wilcoxon tests are not significant because each comparison contains only five nonzero seed-matched pairs; the statistical evidence is therefore interpreted conservatively.

Förderung

  • Guangdong Innovative and Entrepreneurial Research Team Program
  • National Natural Science Foundation of China

Zitieren

APA

Tian, X., Que, C., & Khan, F. N. (2026). Parameter-Efficient Personalized Federated Learning for Accurate Cellular Traffic Prediction. Telecom, 7(4), 104. https://doi.org/10.3390/telecom7040104

Vancouver

Tian X, Que C, Khan FN. Parameter-Efficient Personalized Federated Learning for Accurate Cellular Traffic Prediction. Telecom. 2026;7(4):104. doi:10.3390/telecom7040104

BibTeX
@article{Tian2026,
  author = {Tian, Xingyu and Que, Citong and Khan, Faisal Nadeem},
  title = {Parameter-Efficient Personalized Federated Learning for Accurate Cellular Traffic Prediction},
  journal = {Telecom},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {104},
  doi = {10.3390/telecom7040104}
}
Kostenlos starten →