A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
Irene Balelli1, Santiago Silva1, Marco Lorenzi1
1: Centre INRIA d’Université Côte d'Azur
IPMI 2021 special issue
Publication date: 2022/04/22
Abstract
We propose a novel federated learning paradigm to model data variability among heterogeneous clients in multi-centric studies. Our method is expressed through a hierarchical Bayesian latent variable model, where client-specific parameters are assumed to be realization from a global distribution at the master level, which is in turn estimated to account for data bias and variability across clients. We show that our framework can be effectively optimized through expectation maximization (EM) over latent master's distribution and clients' parameters. We also introduce formal differential privacy (DP) guarantees compatibly with our EM optimization scheme. We tested our method on the analysis of multi-modal medical imaging data and clinical scores from distributed clinical datasets of patients affected by Alzheimer's disease. We demonstrate that our method is robust when data is distributed either in iid and non-iid manners, even when local parameters perturbation is included to provide DP guarantees. Our approach allows to quantify the variability of data, views and centers, while guaranteeing high-quality data reconstruction as compared to the state-of-the-art autoencoding models and federated learning schemes.
The code is available at https://gitlab.inria.fr/epione/federated-multi-views-ppca
Keywords
federated learning · hierarchical generative model · heterogeneity · differential privacy
Bibtex
@article{melba:2022:012:balelli,
title = "A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations",
author = "Balelli, Irene and Silva, Santiago and Lorenzi, Marco",
journal = "Machine Learning for Biomedical Imaging",
volume = "1",
issue = "IPMI 2021 special issue",
year = "2022",
pages = "1--36",
issn = "2766-905X",
url = "https://melba-journal.org/2022:012"
}
RIS
TY - JOUR
AU - Balelli, Irene
AU - Silva, Santiago
AU - Lorenzi, Marco
PY - 2022
TI - A Differentially Private Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations
T2 - Machine Learning for Biomedical Imaging
VL - 1
IS - IPMI 2021 special issue
SP - 1
EP - 36
SN - 2766-905X
UR - https://melba-journal.org/2022:012
ER -
