Inclusive, Differentially Private Federated Learning for Clinical Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912641794965504 |
|---|---|
| author | Parampottupadam, Santhosh Coşğun, Melih Pati, Sarthak Zenk, Maximilian Roy, Saikat Bounias, Dimitrios Hamm, Benjamin Sav, Sinem Floca, Ralf Maier-Hein, Klaus |
| author_facet | Parampottupadam, Santhosh Coşğun, Melih Pati, Sarthak Zenk, Maximilian Roy, Saikat Bounias, Dimitrios Hamm, Benjamin Sav, Sinem Floca, Ralf Maier-Hein, Klaus |
| contents | Federated Learning (FL) offers a promising approach for training clinical AI models without centralizing sensitive patient data. However, its real-world adoption is hindered by challenges related to privacy, resource constraints, and compliance. Existing Differential Privacy (DP) approaches often apply uniform noise, which disproportionately degrades model performance, even among well-compliant institutions. In this work, we propose a novel compliance-aware FL framework that enhances DP by adaptively adjusting noise based on quantifiable client compliance scores. Additionally, we introduce a compliance scoring tool based on key healthcare and security standards to promote secure, inclusive, and equitable participation across diverse clinical settings. Extensive experiments on public datasets demonstrate that integrating under-resourced, less compliant clinics with highly regulated institutions yields accuracy improvements of up to 15% over traditional FL. This work advances FL by balancing privacy, compliance, and performance, making it a viable solution for real-world clinical workflows in global healthcare. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_22108 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Inclusive, Differentially Private Federated Learning for Clinical Data Parampottupadam, Santhosh Coşğun, Melih Pati, Sarthak Zenk, Maximilian Roy, Saikat Bounias, Dimitrios Hamm, Benjamin Sav, Sinem Floca, Ralf Maier-Hein, Klaus Machine Learning Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing Federated Learning (FL) offers a promising approach for training clinical AI models without centralizing sensitive patient data. However, its real-world adoption is hindered by challenges related to privacy, resource constraints, and compliance. Existing Differential Privacy (DP) approaches often apply uniform noise, which disproportionately degrades model performance, even among well-compliant institutions. In this work, we propose a novel compliance-aware FL framework that enhances DP by adaptively adjusting noise based on quantifiable client compliance scores. Additionally, we introduce a compliance scoring tool based on key healthcare and security standards to promote secure, inclusive, and equitable participation across diverse clinical settings. Extensive experiments on public datasets demonstrate that integrating under-resourced, less compliant clinics with highly regulated institutions yields accuracy improvements of up to 15% over traditional FL. This work advances FL by balancing privacy, compliance, and performance, making it a viable solution for real-world clinical workflows in global healthcare. |
| title | Inclusive, Differentially Private Federated Learning for Clinical Data |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2505.22108 |