# Variable selection with false discovery rate control in deep neural networks

arXiv: https://arxiv.org/abs/1909.07561 · HTML: https://mlsanity.com/paper/1909.07561/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2019.

## Built on by (most cited first, 3 of 3)

- [Deep neural networks with controlled variable selection for the identification of putative causal genetic variants](https://mlsanity.com/paper/2109.14719/) (2021)
- [Error Controlled Feature Selection for Ultrahigh Dimensional and Highly Correlated Feature Space Using Deep Learning](https://mlsanity.com/paper/2209.07011/) (2022)
- [A Contrast Based Feature Selection Algorithm for High-dimensional Data set in Machine Learning](https://mlsanity.com/paper/2401.07482/) (2024)

## Abstract (arXiv)

Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability. We consider the problem of variable selection, that is, selecting the input variables that have significant predictive power on the output, in DNNs. We propose a backward elimination procedure called SurvNet, which is based on a new measure of variable importance that applies to a wide variety of networks. More importantly, SurvNet is able to estimate and control the false discovery rate of selected variables, while no existing methods provide such a quality control. Further, SurvNet adaptively determines how many variables to eliminate at each step in order to maximize the selection efficiency. To study its validity, SurvNet is applied to image data and gene expression data, as well as various simulation datasets.