EUVIMEDEUVIMED entdecken
Crossref

SemanticDFL: Similarity-Aware Pull-based Personalized Decentralized Federated Learning

Javad Dogani, Mostafa Khastkhodaei, Farshad Khunjush, Nikolaos Laoutaris

Proceedings of the ACM on Measurement and Analysis of Computing Systems · 29.05.2026 · 10 (2) · 1-37

DOI: 10.1145/3805649 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Measurement and Analysis of Computing Systems, online erschienen am 29.05.2026. Verfasst von Javad Dogani und 3 weiteren Autor:innen. Die Arbeit nennt 73 Literaturangaben. Gefördert von: GenAI4ED.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Personalized decentralized federated learning (PDFL) seeks to tailor models to heterogeneous clients without a central coordinator, yet gossip-style mixing on large graphs dilutes minority signals and assumes any-to-any connectivity. We present SemanticDFL, a fully decentralized, pull-based personalization layer that organizes peers into a hierarchical semantic overlay network (SON). Each client publishes a compact top- P model signature; proximity-bounded discovery forms zones that are clustered using affinity propagation and stewarded by replica-backed super-peers that route bounded-fanout similarity queries. Clients then pull only the K most similar models for personalized aggregation, concentrating communication and computation where they matter most. We prove a lower bound that links spectral mixing and data heterogeneity to an irreducible mis-aggregation penalty for graph-oblivious, push-based overlays, thereby motivating the proposed similarity-aware pull method. A prototype and large-scale evaluation on FMNIST, Tiny ImageNet, Google Speech Commands, and 20 Newsgroups under Dirichlet and pathological splits (50--400 peers on the EU SLICES testbed) show that SemanticDFL improves final accuracy by 3--12% over strong decentralized personalized baselines, reaches target accuracy with ≈2.5× fewer rounds than FedAvg, and requires ≈1.3× fewer rounds than the best DPFL alternative. It adds only ≈1.7--12.6% per-round overhead across all settings while maintaining Recall@K ≈ 0.88--1.00, positioning similarity-aware pull over semantic overlays as a scalable path to high-quality personalization in decentralized FL.

Förderung

  • GenAI4ED

Zitieren

APA

Dogani, J., Khastkhodaei, M., Khunjush, F., & Laoutaris, N. (2026). SemanticDFL: Similarity-Aware Pull-based Personalized Decentralized Federated Learning. Proceedings of the ACM on Measurement and Analysis of Computing Systems, 10(2), 1-37. https://doi.org/10.1145/3805649

Vancouver

Dogani J, Khastkhodaei M, Khunjush F, Laoutaris N. SemanticDFL: Similarity-Aware Pull-based Personalized Decentralized Federated Learning. Proceedings of the ACM on Measurement and Analysis of Computing Systems. 2026;10(2):1-37. doi:10.1145/3805649

BibTeX
@article{Dogani2026,
  author = {Dogani, Javad and Khastkhodaei, Mostafa and Khunjush, Farshad and Laoutaris, Nikolaos},
  title = {SemanticDFL: Similarity-Aware Pull-based Personalized Decentralized Federated Learning},
  journal = {Proceedings of the ACM on Measurement and Analysis of Computing Systems},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {1--37},
  doi = {10.1145/3805649}
}
Kostenlos starten →