EUVIMEDEUVIMED entdecken
Crossref

Heterogeneous Federated Dynamic Graph HyperNetwork for Image Classification

Liu Yang, Kegen Chen, Qilong Wang, Zhengyi Xu, Shiqiao Gu, Qinghua Hu

IEEE Transactions on Image Processing · 2026 · 35 · 3009-3022

DOI: 10.1109/tip.2026.3672375 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Liu Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China, Independent Research Project of State Key Laboratory of Synthetic Biology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables privacy-preserving collaboration among distributed clients, but practical deployments often face heterogeneous models and non-IID data, leading to degraded communication and personalization. In addition, real-world FL systems frequently encounter newly joined clients that require rapid adaptation and abnormal clients that may upload corrupted updates, further exacerbating instability and hindering global convergence. To address these challenges in image classification, we propose HFedDGHN, a Heterogeneous Federated Dynamic Graph HyperNetwork that jointly models inter-client relations and personalized parameter generation. Specifically, a graph structure learner adaptively captures client correlations to construct a dynamic collaboration graph, while a graph-convolutional hypernetwork generates model parameters for heterogeneous architectures, enabling implicit knowledge transfer without sharing local data or weights. Moreover, the framework naturally supports meta-learning-based generalization, allowing efficient adaptation to newly joined clients. Furthermore, the dynamic graph enhances robustness by isolating abnormal clients, as they tend to be excluded from most neighborhoods during adaptive graph construction. Extensive experiments across multiple benchmarks demonstrate that HFedDGHN achieves superior accuracy compared to state-of-the-art personalized and heterogeneous FL methods, while naturally improving robustness and scalability in real-world deployments.

Förderung

  • National Natural Science Foundation of China
  • Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China
  • Independent Research Project of State Key Laboratory of Synthetic Biology

Zitieren

APA

Yang, L., Chen, K., Wang, Q., Xu, Z., Gu, S., & Hu, Q. (2026). Heterogeneous Federated Dynamic Graph HyperNetwork for Image Classification. IEEE Transactions on Image Processing, 35, 3009-3022. https://doi.org/10.1109/tip.2026.3672375

Vancouver

Yang L, Chen K, Wang Q, Xu Z, Gu S, Hu Q. Heterogeneous Federated Dynamic Graph HyperNetwork for Image Classification. IEEE Transactions on Image Processing. 2026;35:3009-3022. doi:10.1109/tip.2026.3672375

BibTeX
@article{Yang2026,
  author = {Yang, Liu and Chen, Kegen and Wang, Qilong and Xu, Zhengyi and Gu, Shiqiao and Hu, Qinghua},
  title = {Heterogeneous Federated Dynamic Graph HyperNetwork for Image Classification},
  journal = {IEEE Transactions on Image Processing},
  year = {2026},
  volume = {35},
  pages = {3009--3022},
  doi = {10.1109/tip.2026.3672375}
}
Kostenlos starten →