Metraipolis › archive › dc_5aaf9efa85ee

FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel — arXiv:2611.05546

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05546
License (as archived)
CC0-1.0
Archived
2026-11-05T18:21:55.292Z
SHA-256 of the archived text
e61bce72b0d2c7faf0abac8bdab33a01574d48cb104eaaf3eece8aef1f5fa1df
Stable URL of this page
https://metraipolis.com/documento/dc_5aaf9efa85ee

How to cite

FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel — arXiv:2611.05546 — arXiv (en), https://arxiv.org/abs/2611.05546 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5aaf9efa85ee (Metraipolis archive dc_5aaf9efa85ee, sha256 e61bce72b0d2c7faf0abac8bdab33a01574d48cb104eaaf3eece8aef1f5fa1df)
BibTeX
@misc{dc5aaf9efa85ee,
  title = {FedSharp: Byzantine Robust Decentralized Federated Learning Under Noisy Channel — arXiv:2611.05546},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05546},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5aaf9efa85ee; sha256 e61bce72b0d2c7faf0abac8bdab33a01574d48cb104eaaf3eece8aef1f5fa1df},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05546. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Decentralized federated learning (DFL) eliminates the central aggregation server but remains vulnerable to data heterogeneity, Byzantine attacks, and channel noise. We show that noise accumulates as models propagate across nodes, becoming increasingly significant as the learning rate decays. Moreover, accumulated noise enables Byzantine attackers to exploit loss-based model selection by mimicking honest model averages. To address these challenges, we propose screened, hop-aware, ranked, proximal averaging, a robust DFL framework (FedSharp). In this approach, each node maintains models from its 2b predecessors, ensuring at least b honest candidates when at most b nodes are Byzantine. FedSharp screens suspicious models using coordinate-wise median deviations, averages the b lowest-loss candidates to reduce fresh channel-noise variance by a factor of b, and applies noise-adaptive gradient-norm regularization and proximal training to mitigate accumulated noise and non-IID drift. Experiments on a 100-node ring with 33 Byzantine nodes show that FedSharp achieves 93.5-94.9% accuracy on MNIST, compared with 29.4-38.1% for a state-of-the-art single-model-selection benchmark, and 32.8-48.8% on CIFAR-10, compared with 10.0-30.5%, across Gaussian and hidden attacks under IID and non-IID data. On MNIST, FedSharp also achieves accuracy within approximately one percentage point of the benchmark operating without channel noise.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.05546 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:15:49.000Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).