Szczegóły publikacji
Opis bibliograficzny
Rule-based federated learning for healthcare / Kamil Woźniak, Jose Sousa, Bartłomiej ŚNIEŻYŃSKI // W: Computational Science – ICCS 2026 : 26th International Conference : Hamburg, Germany, June 29–July 1, 2026 : proceedings , Pt. 1 / eds. Philipp Neumann, [et al.]. — Cham : Springer, cop. 2026. — ( Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 16783 ). — ISBN: 978-3-032-29920-8; e-ISBN: 978-3-032-29921-5. — S. 563–578. — Bibliogr., Abstr. — Publikacja dostępna online od: 2026-06-23
Autorzy (3)
- Woźniak Kamil
- Sousa Jose
- AGHŚnieżyński Bartłomiej
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 168879 |
|---|---|
| Data dodania do BaDAP | 2026-08-28 |
| DOI | 10.1007/978-3-032-29921-5_38 |
| Rok publikacji | 2026 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Computational Science 2026 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
This paper investigates the adaptation of classical rule-based classification algorithms (LEM2, PRISM, and RIPPER) to the federated learning paradigm. We propose a federation discretization framework that establishes global bin boundaries using aggregated feature statistics, ensuring consistent rule vocabulary across clients without sharing raw data. We conducted experiments on five medical datasets, which had varying numbers of clients (2–5) and discretization granularities (2–7 bins), with all configurations evaluated across 5 random data splits. The results show that the global model consistently achieves high levels of predictive accuracy and interpretability, outperforming averaged results of local models by 7.0–9.1% in balanced accuracy across algorithms. Notably, federated LEM2 significantly outperformed even its centralized counterpart (p=0.011), while federated RIPPER and PRISM achieved statistical parity with centralized baselines (p>0.05). On average, the resulting rulesets are compact (8.3–53.1 rules) and interpretable (1.39–4.26 conditions per rule), with coverage ranging from 51% to 96% depending on the algorithm. These results demonstrate that federated rule learning can provide both transparency and competitive performance for clinical applications where data is limited and privacy is essential.
