Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data - Archive ouverte HAL Access content directly
Conference Papers Year :

Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data

(1) , (1) , (2, 3) , (1)
1
2
3

Abstract

Interpretable modeling of heterogeneous data channels is essential in medical applications, for example when jointly analyzing clinical scores and medical images. Variational Autoencoders (VAE) are powerful generative models that learn representations of complex data. The flexibility of VAE may come at the expense of lack of interpretability in describing the joint relationship between heterogeneous data. To tackle this problem, in this work we extend the variational framework of VAE to bring parsimony and inter-pretability when jointly account for latent relationships across multiple channels. In the latent space, this is achieved by constraining the varia-tional distribution of each channel to a common target prior. Parsimonious latent representations are enforced by variational dropout. Experiments on synthetic data show that our model correctly identifies the prescribed latent dimensions and data relationships across multiple testing scenarios. When applied to imaging and clinical data, our method allows to identify the joint effect of age and pathology in describing clinical condition in a large scale clinical cohort.
Fichier principal
Vignette du fichier
antelmi19a.pdf (751.63 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02154181 , version 1 (12-06-2019)

Identifiers

  • HAL Id : hal-02154181 , version 1

Cite

Luigi Antelmi, Nicholas Ayache, Philippe Robert, Marco Lorenzi. Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data. ICML 2019 - 36th International Conference on Machine Learning, Jun 2019, Long Beach, United States. ⟨hal-02154181⟩
167 View
828 Download

Share

Gmail Facebook Twitter LinkedIn More