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

arXiv: https://arxiv.org/abs/2505.22108 · HTML: https://mlsanity.com/paper/2505.22108/

## Key facts

- Cited by 1 papers 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 (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Adaptive Federated Optimization](https://mlsanity.com/paper/2003.00295/) (2020)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Flower: A Friendly Federated Learning Research Framework](https://mlsanity.com/paper/2007.14390/) (2020)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Robust Aggregation for Federated Learning](https://mlsanity.com/paper/1912.13445/) (2019)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [Numerical Composition of Differential Privacy](https://mlsanity.com/paper/2106.02848/) (2021)
- [Federated Learning Enables Big Data for Rare Cancer Boundary Detection](https://mlsanity.com/paper/2204.10836/) (2022)
- [Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification](https://mlsanity.com/paper/2202.00580/) (2022)
- [Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy](https://mlsanity.com/paper/2205.10683/) (2022)
- [Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping](https://mlsanity.com/paper/2009.03106/) (2020)
- [Heterogeneous Differential Privacy](https://mlsanity.com/paper/1504.06998/) (2015)
- [Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment](https://mlsanity.com/paper/2304.06929/) (2023)
- [Data Leakage in Federated Averaging](https://mlsanity.com/paper/2206.12395/) (2022)
- [Have it your way: Individualized Privacy Assignment for DP-SGD](https://mlsanity.com/paper/2303.17046/) (2023)
- [From Challenges and Pitfalls to Recommendations and Opportunities: Implementing Federated Learning in Healthcare](https://mlsanity.com/paper/2409.09727/) (2024)
- [Fine-Tuning Language Models with Differential Privacy through Adaptive Noise Allocation](https://mlsanity.com/paper/2410.02912/) (2024)
- [Belt and Braces: When Federated Learning Meets Differential Privacy](https://mlsanity.com/paper/2404.18814/) (2024)
- [DuetSGX: Differential Privacy with Secure Hardware](https://mlsanity.com/paper/2010.10664/) (2020)

## Built on by (most cited first, 1 of 1)

- [CFL-SparseMed: Communication-Efficient Federated Learning for Medical Imaging with Top-k Sparse Updates](https://mlsanity.com/paper/2510.24776/) (2025)

## 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.