Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning
In the data-driven healthcare sector, balancing privacy protection and model performance is critical. This paper enhances accuracy and reliability in survival analysis by integrating differential privacy, deep learning, and the Cox proportional hazards model within a federated learning framework. Tr...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/7/1096 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849730335727681536 |
|---|---|
| author | Jie Niu Runqi He Qiyao Zhou Wenjing Li Ruxian Jiang Huimin Li Dan Chen |
| author_facet | Jie Niu Runqi He Qiyao Zhou Wenjing Li Ruxian Jiang Huimin Li Dan Chen |
| author_sort | Jie Niu |
| collection | DOAJ |
| description | In the data-driven healthcare sector, balancing privacy protection and model performance is critical. This paper enhances accuracy and reliability in survival analysis by integrating differential privacy, deep learning, and the Cox proportional hazards model within a federated learning framework. Traditionally, differential privacy’s noise injection often degrades model performance. To address this, we propose two adaptive privacy budget allocation strategies considering weight changes across neural network layers. The first, LS-ADP, utilizes layer sensitivity to assess the influence of individual layer weights on model performance and develops an adaptive differential privacy algorithm. The second, ROW-DP, comprehensively assesses weight variations and absolute values to propose a random one-layer weighted differential privacy algorithm. These algorithms provide differentiated privacy protection for various weights, mitigating privacy leakage while ensuring model performance. Experimental results on simulated and clinical datasets demonstrate improved predictive performance and robust privacy protection. |
| format | Article |
| id | doaj-art-88ceb06f6f3b4bdd85ad195c7d4cbefa |
| institution | DOAJ |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-88ceb06f6f3b4bdd85ad195c7d4cbefa2025-08-20T03:08:55ZengMDPI AGMathematics2227-73902025-03-01137109610.3390/math13071096Adaptive Differential Privacy Cox-MLP Model Based on Federated LearningJie Niu0Runqi He1Qiyao Zhou2Wenjing Li3Ruxian Jiang4Huimin Li5Dan Chen6Yunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaYunnan Key Laboratory of Statistical Modeling and Data Analysis, Yunnan University, Kunming 650500, ChinaIn the data-driven healthcare sector, balancing privacy protection and model performance is critical. This paper enhances accuracy and reliability in survival analysis by integrating differential privacy, deep learning, and the Cox proportional hazards model within a federated learning framework. Traditionally, differential privacy’s noise injection often degrades model performance. To address this, we propose two adaptive privacy budget allocation strategies considering weight changes across neural network layers. The first, LS-ADP, utilizes layer sensitivity to assess the influence of individual layer weights on model performance and develops an adaptive differential privacy algorithm. The second, ROW-DP, comprehensively assesses weight variations and absolute values to propose a random one-layer weighted differential privacy algorithm. These algorithms provide differentiated privacy protection for various weights, mitigating privacy leakage while ensuring model performance. Experimental results on simulated and clinical datasets demonstrate improved predictive performance and robust privacy protection.https://www.mdpi.com/2227-7390/13/7/1096federated learningdifferential privacysurvival analysisCox proportional hazards model |
| spellingShingle | Jie Niu Runqi He Qiyao Zhou Wenjing Li Ruxian Jiang Huimin Li Dan Chen Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning Mathematics federated learning differential privacy survival analysis Cox proportional hazards model |
| title | Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning |
| title_full | Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning |
| title_fullStr | Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning |
| title_full_unstemmed | Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning |
| title_short | Adaptive Differential Privacy Cox-MLP Model Based on Federated Learning |
| title_sort | adaptive differential privacy cox mlp model based on federated learning |
| topic | federated learning differential privacy survival analysis Cox proportional hazards model |
| url | https://www.mdpi.com/2227-7390/13/7/1096 |
| work_keys_str_mv | AT jieniu adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning AT runqihe adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning AT qiyaozhou adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning AT wenjingli adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning AT ruxianjiang adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning AT huiminli adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning AT danchen adaptivedifferentialprivacycoxmlpmodelbasedonfederatedlearning |