# Dropout Feature Ranking for Deep Learning Models

arXiv: https://arxiv.org/abs/1712.08645 · HTML: https://mlsanity.com/paper/1712.08645/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2017.

## Built on by (most cited first, 13 of 13)

- [Learning to Maximize Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2301.00557/) (2023)
- [Estimating Conditional Mutual Information for Dynamic Feature Selection](https://mlsanity.com/paper/2306.03301/) (2023)
- [Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking: A Learnable Feature Selection based Approach](https://mlsanity.com/paper/2105.07706/) (2021)
- [Deep IDA: A Deep Learning Method for Integrative Discriminant Analysis of Multi-View Data with Feature Ranking -- An Application to COVID-19 severity](https://mlsanity.com/paper/2111.09964/) (2021)
- [Lazy Estimation of Variable Importance for Large Neural Networks](https://mlsanity.com/paper/2207.09097/) (2022)
- [Synthesizing Speech from Intracranial Depth Electrodes using an Encoder-Decoder Framework](https://mlsanity.com/paper/2111.01457/) (2021)
- [Reliable and scalable variable importance estimation via warm-start and early stopping](https://mlsanity.com/paper/2412.01120/) (2024)
- [Reverse Survival Model (RSM): A Pipeline for Explaining Predictions of Deep Survival Models](https://mlsanity.com/paper/2210.15674/) (2022)
- [Dropout Concrete Autoencoder for Band Selection on HSI Scenes](https://mlsanity.com/paper/2401.16522/) (2024)
- [Dealing with missing data using attention and latent space regularization](https://mlsanity.com/paper/2211.07059/) (2022)
- [DTN: Deep Multiple Task-specific Feature Interactions Network for Multi-Task Recommendation](https://mlsanity.com/paper/2408.11611/) (2024)
- [Comparing Model-agnostic Feature Selection Methods through Relative Efficiency](https://mlsanity.com/paper/2508.14268/) (2025)
- [FairFS: Addressing Deep Feature Selection Biases for Recommender System](https://mlsanity.com/paper/2602.20001/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) achieve state-of-the-art results in a variety of domains. Unfortunately, DNNs are notorious for their non-interpretability, and thus limit their applicability in hypothesis-driven domains such as biology and healthcare. Moreover, in the resource-constraint setting, it is critical to design tests relying on fewer more informative features leading to high accuracy performance within reasonable budget. We aim to close this gap by proposing a new general feature ranking method for deep learning. We show that our simple yet effective method performs on par or compares favorably to eight strawman, classical and deep-learning feature ranking methods in two simulations and five very different datasets on tasks ranging from classification to regression, in both static and time series scenarios. We also illustrate the use of our method on a drug response dataset and show that it identifies genes relevant to the drug-response.