EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Objective Federated Learning via Evolutionary Knowledge Transfer

Zhiyuan Li, Chenhui Ju, Hao Li, Maoguo Gong

Applied Sciences · 20.05.2026 · 16 (10) · 5094

DOI: 10.3390/app16105094 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 20.05.2026. Verfasst von Zhiyuan Li und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning enables multiple clients to collaboratively train a global model without exchanging raw data, thereby alleviating data silos and privacy concerns. However, federated learning model design is still challenged by complex architecture and hyperparameter optimization, especially under heterogeneous data distributions. To address these issues, this paper proposes a multi-objective federated learning framework based on particle swarm optimization (PSO). Specifically, neural architecture search and training-parameter optimization are formulated as a multi-objective evolutionary optimization problem, where predictive performance and model complexity are optimized jointly. Furthermore, to improve robustness under non-independent and identically distributed (non-IID) data, a clustered multi-population extension is developed. In this framework, each cluster is associated with a dedicated particle population. An inter-population evolutionary knowledge transfer mechanism is then introduced to enable effective sharing of search experience across clusters, thereby improving the optimization efficiency and adaptability of federated learning under heterogeneous environments. Experiments on MNIST and CIFAR10 under both IID and non-IID settings demonstrate that the proposed methods achieve a superior trade-off between predictive accuracy and model complexity and outperform baseline approaches in robustness, search efficiency, and adaptability to imbalanced distributed environments.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Ju, C., Li, H., & Gong, M. (2026). Multi-Objective Federated Learning via Evolutionary Knowledge Transfer. Applied Sciences, 16(10), 5094. https://doi.org/10.3390/app16105094

Vancouver

Li Z, Ju C, Li H, Gong M. Multi-Objective Federated Learning via Evolutionary Knowledge Transfer. Applied Sciences. 2026;16(10):5094. doi:10.3390/app16105094

BibTeX
@article{Li2026,
  author = {Li, Zhiyuan and Ju, Chenhui and Li, Hao and Gong, Maoguo},
  title = {Multi-Objective Federated Learning via Evolutionary Knowledge Transfer},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {10},
  pages = {5094},
  doi = {10.3390/app16105094}
}
Kostenlos starten →