Learning a Sparse Generative Non-Parametric Supervised Autoencoder

Barlaud, Michel; Guyard, Frédéric

doi:10.1109/icassp39728.2021.9414410

Cited by 9 publications

(24 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal is to compute the weights W minimizing the total loss, which depends on both the classification loss and the reconstruction loss. Thus, we propose to minimize the following criterion to compute the weights W of the autoencoder (see [17] for details).…”

Section: A New Supervised Autoencoder (Sae) Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

et al. 2022

Self Cite

View full text Add to dashboard Cite

Background Presently, there is a wide variety of classification methods and deep neural network approaches in bioinformatics. Deep neural networks have proven their effectiveness for classification tasks, and have outperformed classical methods, but they suffer from a lack of interpretability. Therefore, these innovative methods are not appropriate for decision support systems in healthcare. Indeed, to allow clinicians to make informed and well thought out decisions, the algorithm should provide the main pieces of information used to compute the predicted diagnosis and/or prognosis, as well as a confidence score for this prediction. Methods Herein, we used a new supervised autoencoder (SAE) approach for classification of clinical metabolomic data. This new method has the advantage of providing a confidence score for each prediction thanks to a softmax classifier and a meaningful latent space visualization and to include a new efficient feature selection method, with a structured constraint, which allows for biologically interpretable results. Results Experimental results on three metabolomics datasets of clinical samples illustrate the effectiveness of our SAE and its confidence score. The supervised autoencoder provides an accurate localization of the patients in the latent space, and an efficient confidence score. Experiments show that the SAE outperforms classical methods (PLS-DA, Random Forests, SVM, and neural networks (NN)). Furthermore, the metabolites selected by the SAE were found to be biologically relevant. Conclusion In this paper, we describe a new efficient SAE method to support diagnostic or prognostic evaluation based on metabolomics analyses.

show abstract

Section: A New Supervised Autoencoder (Sae) Frameworkmentioning

confidence: 99%

“…In this work, we relaxed the parametric distribution assumption on the latent space to learn a non-parametric data distribution of clusters [17]. Our network encourages the latent space to fit a distribution learned with the clustering labels rather than a parametric prior.…”

mentioning

confidence: 99%

Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Criterionmentioning

confidence: 99%

“…Moreover the "group Lasso ℓ 2,1 constraint" induces small sparsity [39] and the ℓ 1 constraint induces unstructured sparsity [40,41]. Thus we used ℓ 1,1 constrained regularization penalty W 1 1 ≤ η for feature selection [25].…”

Section: Structured Constrains Sparsity and Feature Selectionmentioning

confidence: 99%

“…mixtures of Gaussians [22,23,24]) on the latent vectors, but they are non-adaptive and unfortunately may not match the specific data distribution. In this work, we relaxed the parametric distribution assumption on the latent space to learn a non-parametric data distribution of clusters [25]. Our network encourages the latent space to fit a distribution learned with the clustering labels rather than a parametric prior.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning a confidence score and the latent space of a new Supervised Autoencoder for diagnosis and prognosis in clinical metabolomic studies

Barlaud

Chardin

Gille

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Presently, there is a wide variety of classification methods and deep neural networks approaches in bioinformatics. Deep neural networks have proven their effectiveness for classification tasks, and have outperformed classical methods, but they suffer from a lack of interpretability. Therefore, these innovative methods are not appropriate for decision support systems in healthcare. The algorithm should provide the main pieces of information allowing computed diagnosis and prognosis for the final decision by the clinician. To address this lack of interpretability, we used a new supervised autoencoder (SAE). The main advantage of our supervised autoencoder is its ability to provide a diagnosis with a confidence score for each patient thanks to a softmax classifier, and a meaningful latent space visualization. This confidence score and visual evaluation are crucial for clinical interpretability. Moreover, we used a new efficient feature selection method with a structured constraint for biologically interpretable results. Experimental results on three metabolomics datasets of clinical samples illustrate the effectiveness of our confidence score diagnostic method: Results: The supervised autoencoder provides an accurate localization of the patients in the latent space, and an efficient confidence score. Experiments show that the SAE outperforms classical methods (PLS-DA, Random Forests, SVM, and neural networks (NN)). Furthermore, the metabolites selected by the SAE were found to be relevant. Conclusion: In this paper, we have proposed a new efficient method for diagnosis or prognosis support using clinical metabolomics analyses.

show abstract