Metraipolis › archive › dc_3fd7618297bf
When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data — arXiv:2610.05598
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.05598
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:27:02.572Z
- SHA-256 of the archived text
6546833a5e03a3813de4a8ea14b50d5be7117e0db8475854147653e4c484204e- Stable URL of this page
https://metraipolis.com/documento/dc_3fd7618297bf
How to cite
When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data — arXiv:2610.05598 — arXiv, https://arxiv.org/abs/2610.05598 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3fd7618297bf (Metraipolis archive dc_3fd7618297bf, sha256 6546833a5e03a3813de4a8ea14b50d5be7117e0db8475854147653e4c484204e)
BibTeX
@misc{dc3fd7618297bf,
title = {When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data — arXiv:2610.05598},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.05598},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3fd7618297bf; sha256 6546833a5e03a3813de4a8ea14b50d5be7117e0db8475854147653e4c484204e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05598. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
An organization often holds too little labeled data to train a model that generalizes, and the records that would supply the rest sit with organizations that cannot release them. Cross-silo federated learning offers a way through, since participants exchange model parameters rather than records, but it ordinarily settles two aspects of the arrangement in advance, the participating sites and the classes the model can predict, and deployment can breach both. A new site joins after training, once the established sites have finished their engagement and gone offline, and its records arrive unlabeled, mixing conditions the model already recognizes with conditions no participant has observed. We present an autonomous three-stage procedure that expands the model entirely at the joining site: reconstruction experts screen for novelty, clustering separates the flagged records into candidate conditions, and class means describe the old classes, all inside one shared representation. Those classes were learned from records that never leave their owners, so the usual defenses against forgetting are unavailable, and the procedure supplies the evidence they would have carried from either of two dissimilar sources, prototypes held by the federation or records held by the joining site. On a real industrial condition-monitoring dataset, run end to end with no label consulted, either source holds old-class accuracy at 0.868 or above with forgetting at most 0.063, and the two differ by 0.021, so a configuration can be chosen by the disclosure it permits rather than the accuracy it delivers. Both keep old- and new-class accuracy in balance where every alternative we measure gives up one for the other, and both retain more of the old classes than distillation- and regularization-based baselines. The balance still holds with only 6 labeled records per arriving condition and 3 retained per old class. 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). Pagina del lavoro: https://arxiv.org/abs/2610.05598 — 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 2026-10-06T05:24:06.050Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).