Metraipolis › archive › dc_4356bfa9bd15
One-Shot Federated Model Editing for Device Dynamics at the Edge — arXiv:2610.35212
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35212
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:02:34.810Z
- SHA-256 of the archived text
69b1da69ec9a127240f28b1f0778c07f1e5e0de86b5e6f6417aef5421eac67f7- Stable URL of this page
https://metraipolis.com/documento/dc_4356bfa9bd15
How to cite
One-Shot Federated Model Editing for Device Dynamics at the Edge — arXiv:2610.35212 — arXiv (en), https://arxiv.org/abs/2610.35212 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4356bfa9bd15 (Metraipolis archive dc_4356bfa9bd15, sha256 69b1da69ec9a127240f28b1f0778c07f1e5e0de86b5e6f6417aef5421eac67f7)
BibTeX
@misc{dc4356bfa9bd15,
title = {One-Shot Federated Model Editing for Device Dynamics at the Edge — arXiv:2610.35212},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35212},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4356bfa9bd15; sha256 69b1da69ec9a127240f28b1f0778c07f1e5e0de86b5e6f6417aef5421eac67f7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35212. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Standard federated learning (FL) requires persistent device connectivity across multiple communication rounds, making it unsuitable for dynamic environments such as vehicular networks, where devices frequently join and leave. One-shot FL offers a promising alternative by completing training in a single communication round. However, one-shot FL suffers from model solidification and cannot readily adapt to subsequent client dynamics, including new client contributions and the withdrawal of previous contributions. We therefore consider exact model editing, which removes withdrawn contributions through unlearning or incorporates newly contributed ones through incremental learning without retraining from scratch. We identify that efficient editing fundamentally hinges on learning stability. To this end, we propose F-SOSA, the first stable one-shot FL algorithm that enables rapid and exact model editing. F-SOSA leverages sub-sampling of local models with carefully tuned rate for stable aggregation and performs curvature-aware model fusion to preserve utility. We prove that F-SOSA achieves vanishing training error and reasonably small generalization error bounds. Building on this stability, we further develop two single-round editing algorithms: F-SOSA-U for unlearning and F-SOSA-I for incremental learning. They ensure that the edited model, along with all intermediate algorithmic states, is statistically indistinguishable from retraining while incurring only an expected $O(\rho)$ fraction of its cost, where $\rho$ quantifies stability. Experiments demonstrate that our approach matches retraining performance while reducing cumulative time and communication overhead by at least 36% and 22%, respectively, under realistic urban mobility simulations. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2610.35212 — 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 2026-10-27T07:55:30.973Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).