EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Bridging structural and statistical heterogeneity: a unified DFL framework via column-wise aggregation and consensus-aware topology

Su Liu, Hong Shen, Ka Lun Eddie Law, Chan-Tong LAM

Journal of King Saud University Computer and Information Sciences · 2026-08 · 38 (6)

DOI: 10.1007/s44443-026-00911-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of King Saud University Computer and Information Sciences, online erschienen am 10.06.2026. Verfasst von Su Liu und 3 weiteren Autor:innen. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Decentralized Federated Learning (DFL) is an emerging paradigm that enables collaborative model training across distributed clients without relying on a central parameter server. However, deploying DFL in realistic edge environments faces two critical limitations: structural heterogeneity among local models due to varying computational capabilities of client nodes, and model divergence caused by statistical heterogeneity (non-IID data) within static or inefficient communication topologies. While prior works have tackled these challenges individually, a unified perspective on their synergistic optimization is still lacking. In this paper, we introduce ColADTM-DFL framework, which jointly addresses structural and statistical heterogeneity in a single system workflow. First, ColADTM-DFL enables each node to train a width-adaptive submodel while ensuring semantically aligned parameter fusion. Then, considering the model divergence exacerbated by statistical heterogeneity, our framework defines Consensus Distance to quantify inter-node model discrepancy. Leveraging this metric, we present a consensus-aware topology algorithm, which dynamically restructures the communication graph to minimize global divergence while reducing redundant communication cost. Extensive experiments across heterogeneous edge settings demonstrate that our method significantly accelerates time-to-target accuracy, as well as reduces communication cost by up to 46.3% under the same resource budget compared to baselines.

Zitieren

APA

Liu, S., Shen, H., Law, K. L. E., & LAM, C. (2026). Bridging structural and statistical heterogeneity: a unified DFL framework via column-wise aggregation and consensus-aware topology. Journal of King Saud University Computer and Information Sciences, 38(6). https://doi.org/10.1007/s44443-026-00911-3

Vancouver

Liu S, Shen H, Law KLE, LAM C. Bridging structural and statistical heterogeneity: a unified DFL framework via column-wise aggregation and consensus-aware topology. Journal of King Saud University Computer and Information Sciences. 2026;38(6). doi:10.1007/s44443-026-00911-3

BibTeX
@article{Liu2026,
  author = {Liu, Su and Shen, Hong and Law, Ka Lun Eddie and LAM, Chan-Tong},
  title = {Bridging structural and statistical heterogeneity: a unified DFL framework via column-wise aggregation and consensus-aware topology},
  journal = {Journal of King Saud University Computer and Information Sciences},
  year = {2026},
  volume = {38},
  number = {6},
  doi = {10.1007/s44443-026-00911-3}
}
Kostenlos starten →