Skip to Main content Skip to Navigation
Journal articles

A Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations

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 over latent master's distribution and clients' parameters. 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: it 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03152886
Contributor : Irene Balelli Connect in order to contact the contributor
Submitted on : Wednesday, March 24, 2021 - 1:45:51 PM
Last modification on : Wednesday, October 13, 2021 - 3:39:34 AM

File

Balelli_IPMI2021_CameraReady.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03152886, version 2
`

Citation

Irene Balelli, Santiago Silva, Marco Lorenzi. A Probabilistic Framework for Modeling the Variability Across Federated Datasets of Heterogeneous Multi-View Observations. Information processing in medical imaging : proceedings of the .. conference., Springer-Verlag, In press. ⟨hal-03152886v2⟩

Share

Metrics

Record views

143

Files downloads

323