mlsanityData to 14 Oct 2026

Inclusive Federated Learning Through Compliance-Weighted Noise Allocation in Healthcare AI

arXiv 2505.22108 ↗First posted 28 May 2025cs.LG cs.AI cs.CRcited by 1

Not on the map. Why?

Abstract (arXiv)

Background: Federated learning (FL) enables collaborative training of clinical AI models without centralizing patient data, but adoption is limited by privacy concerns, heterogeneous institutional compliance, and resource disparities; standard differential privacy (DP) applies uniform noise to all clients, penalizing well-compliant or under-resourced institutions. Objective: We introduce a compliance-aware FL framework that adapts DP to institutional compliance, letting lower-compliance sites participate without uniformly penalizing others. Methods: A compliance scoring tool aligned with HIPAA, GDPR, NIST, ISO, and HL7/FHIR maps each client score to a per-step Gaussian noise scale for server-side DP-SGD on a small aggregator dataset. The formal (ε,δ) bound applies to the aggregator dataset under a semi-honest aggregator; client-level DP needs secure aggregation (future work). We evaluate five FL strategies on PneumoniaMNIST and BreastMNIST (16 clients, 50 rounds, five seeds); the cumulative aggregator-dataset ε is about 1434 (Breast) and 513 (Pneumonia) at δ=10-5. Results: Including 12 lower-compliance clients (Experiment 1) versus a compliant-only baseline (Experiment 4) changed BreastMNIST accuracy by +4.5 (FedAvg), +6.8 (FedMedian), +5.2 (FedProx), +1.6 (FedYogi), and -4.1 (FedAdam) percentage points (pooled +2.8 pp; not significant at n=5; up to +17 pp per configuration); compliance-weighted allocation matched uniform server-side DP at equal mean noise (+0.1 pp), carrying no utility penalty, and first-round noise cost 1.3 pp (Breast) and 2.5 pp (Pneumonia, FedAvg). Conclusions: Compliance-weighted server-side DP lets lower-compliance institutions join FL without degrading performance, giving auditable per-site noise control at no utility cost; formal guarantees apply to the aggregator dataset, with client-level DP requiring secure aggregation.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 58 references that are in the map. First posted on arXiv 28 May 2025.

Builds on

26 of 58 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2020Adaptive Federated Optimizationcited by 1,046
  6. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  7. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  8. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  9. 2017Renyi Differential Privacycited by 650
  10. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 455
  11. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  12. 2019Robust Aggregation for Federated Learningcited by 317
14 more
  1. 2019Differential Privacy Has Disparate Impact on Model Accuracycited by 316
  2. 2021Numerical Composition of Differential Privacycited by 180
  3. 2022Federated Learning Enables Big Data for Rare Cancer Boundary Detectioncited by 84
  4. 2022Fishing for User Data in Large-Batch Federated Learning via Gradient Magnificationcited by 73
  5. 2022Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacycited by 48
  6. 2020Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clippingcited by 47
  7. 2015Heterogeneous Differential Privacycited by 30
  8. 2023Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deploymentcited by 27
  9. 2022Data Leakage in Federated Averagingcited by 26
  10. 2023Have it your way: Individualized Privacy Assignment for DP-SGDcited by 21
  11. 2024From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcarecited by 16
  12. 2024Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocationcited by 14
  13. 2024Belt and Braces: When Federated Learning Meets Differential Privacycited by 4
  14. 2020DuetSGX: Differential Privacy with Secure Hardwarecited by 1

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025CFL-SparseMed: Communication-Efficient Federated Learning for Medical Imaging with Top-k Sparse Updatescited by 0