Skip to Main content Skip to Navigation
New interface
Journal articles

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

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.
Complete list of metadata

Cited literature [38 references]  Display  Hide  Download
Contributor : Luigi Antelmi Connect in order to contact the contributor
Submitted on : Thursday, December 5, 2019 - 4:25:19 PM
Last modification on : Thursday, August 4, 2022 - 4:54:52 PM
Long-term archiving on: : Friday, March 6, 2020 - 5:40:45 PM


Files produced by the author(s)


  • HAL Id : hal-02395747, version 1


Luigi Antelmi, Nicholas Ayache, Philippe Robert, Marco Lorenzi. Sparse Multi-Channel Variational Autoencoder for the Joint Analysis of Heterogeneous Data. Proceedings of Machine Learning Research, 2019, Proceedings of ICML 2019, 97, pp.302--311. ⟨hal-02395747⟩



Record views


Files downloads