Metraipolis › archive › dc_4fcfd499067d
Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration — arXiv:2609.07312
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.07312
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:07:31.805Z
- SHA-256 of the archived text
2764be6fcfaf3229550c6b09f7d0569635fa8b5b806445c6f96e12250900deba- Stable URL of this page
https://metraipolis.com/documento/dc_4fcfd499067d
How to cite
Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration — arXiv:2609.07312 — arXiv (en), https://arxiv.org/abs/2609.07312 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4fcfd499067d (Metraipolis archive dc_4fcfd499067d, sha256 2764be6fcfaf3229550c6b09f7d0569635fa8b5b806445c6f96e12250900deba)
BibTeX
@misc{dc4fcfd499067d,
title = {Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration — arXiv:2609.07312},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.07312},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4fcfd499067d; sha256 2764be6fcfaf3229550c6b09f7d0569635fa8b5b806445c6f96e12250900deba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07312. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine attacks via robust neighborhood direction estimation and history-based update trend prediction, rather than purely aggregating client models as in the existing work. In R-DPFL, each client first computes the current-round model update by aggregating the received neighborhood update vectors. It then predicts what this update should be based on its historical values and local model changes. Finally, R-DPFL computes the difference between these two quantities, adaptively clips this difference, and adds it to the local update. We prove convergence of the learning process through rigorous analysis and show that honest clients maintain stable personalized descent dynamics under Byzantine neighbor perturbations without requiring consensus among neighboring models. Extensive experiments on CIFAR-10 demonstrate that RDPFL consistently outperforms state-of-the-art decentralized and personalized federated learning baselines under heterogeneous and adversarial settings. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.DC). Categorie arXiv: Machine Learning (cs.LG) ; Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC). Pagina del lavoro: https://arxiv.org/abs/2609.07312 — 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 2026-10-16T13:02:21.619Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).