Metraipolis › archive › dc_51df7057728d
Differential Privacy Synthetic Tabular Data Generation for Federated Learning (2026) · DOI 10.20944/preprints202608.1914.v1
- Source
- Metraipolis archive
- Original
- https://doi.org/10.20944/preprints202608.1914.v1
- License (as archived)
- CC-BY-4.0
- Archived
- 2026-10-08T00:02:59.736Z
- SHA-256 of the archived text
f68e09520d44c46cc0d076bae1420ff722db36555d562d831bfa3578679dc692- Stable URL of this page
https://metraipolis.com/documento/dc_51df7057728d
How to cite
Differential Privacy Synthetic Tabular Data Generation for Federated Learning (2026) · DOI 10.20944/preprints202608.1914.v1 — Metraipolis archive, https://doi.org/10.20944/preprints202608.1914.v1 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_51df7057728d (Metraipolis archive dc_51df7057728d, sha256 f68e09520d44c46cc0d076bae1420ff722db36555d562d831bfa3578679dc692)
BibTeX
@misc{dc51df7057728d,
title = {Differential Privacy Synthetic Tabular Data Generation for Federated Learning (2026) · DOI 10.20944/preprints202608.1914.v1},
howpublished = {Metraipolis archive},
url = {https://doi.org/10.20944/preprints202608.1914.v1},
note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_51df7057728d; sha256 f68e09520d44c46cc0d076bae1420ff722db36555d562d831bfa3578679dc692},
year = {2026}
}Archived text
Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://doi.org/10.20944/preprints202608.1914.v1. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Articolo recente con licenza aperta: scheda dai metadati Crossref (posted-content). Titolo: Differential Privacy Synthetic Tabular Data Generation for Federated Learning Autori: Mariona Almató-Baucells, Carla Lázaro, Cecilio Angulo Pubblicato: 2026-08-26 · editore: MDPI AG DOI: https://doi.org/10.20944/preprints202608.1914.v1 Licenza dell'articolo: CC-BY-4.0 Abstract (testo degli autori, CC-BY-4.0): Machine learning in healthcare struggles for one main reason: good data is hard to come by. Medical records are sensitive, and the rules on sharing them between hospitals are strict. A common workaround is synthetic data, that is artificial records that copy the statistics of real ones; however, on its own, it offers no real privacy guarantee, and earlier studies show it can still leak details about the patients behind it. We introduce an approach tackling both problems at once. It builds on a previous UMAP-based generator methodology and extends it so several hospitals can work together without sharing raw records, in a federated learning form. Then, the proposed methodology adds differential privacy so every shared quantity carries a formal (εDP,δ) guarantee, tracked by a custom privacy accountant. Two versions of the methodology are tested: a partially synthetic one, where a reference hospital validates the others’ rows, and a fully synthetic one, where each centre builds its own data from aggregated cluster statistics. Both are evaluated on four publicly available healthcare tabular datasets spanning prostate cancer (PI-CAI, CIA), breast cancer (BC-MLR), and cardiovascular disease (fiv-CardioDB), to test whether the observed trends generalize beyond a single clinical domain. As a key takeaway, it is demonstrated that going federated barely affects quality, but the privacy cost depends strongly on the moment in the procedure when the noise is injected, and this pattern holds consistently across all four datasets. Fonte: https://api.crossref.org/works/10.20944%2Fpreprints202608.1914.v1 — metadati Crossref, consultati il 2026-10-07. Interrogazione: «federated learning privacy».