# Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks

arXiv: https://arxiv.org/abs/2606.04404 · HTML: https://mlsanity.com/paper/2606.04404/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Builds on (most cited first, 17 of 17)

- [Training generative neural networks via Maximum Mean Discrepancy optimization](https://mlsanity.com/paper/1505.03906/) (2015)
- [Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selection](https://mlsanity.com/paper/1610.02351/) (2016)
- [Controlling the false discovery rate via knockoffs](https://mlsanity.com/paper/1404.5609/) (2014)
- [Model Selection in Bayesian Neural Networks via Horseshoe Priors](https://mlsanity.com/paper/1705.10388/) (2017)
- [DeepPINK: reproducible feature selection in deep neural networks](https://mlsanity.com/paper/1809.01185/) (2018)
- [Deep Knockoffs](https://mlsanity.com/paper/1811.06687/) (2018)
- [Efficient Variational Inference for Sparse Deep Learning with Theoretical Guarantee](https://mlsanity.com/paper/2011.07439/) (2020)
- [Consistent Feature Selection for Analytic Deep Neural Networks](https://mlsanity.com/paper/2010.08097/) (2020)
- [A knockoff filter for high-dimensional selective inference](https://mlsanity.com/paper/1602.03574/) (2016)
- [Statistical Guarantees for Regularized Neural Networks](https://mlsanity.com/paper/2006.00294/) (2020)
- [Gene Hunting with Knockoffs for Hidden Markov Models](https://mlsanity.com/paper/1706.04677/) (2017)
- [Sequential Attention for Feature Selection](https://mlsanity.com/paper/2209.14881/) (2022)
- [Deep neural networks with controlled variable selection for the identification of putative causal genetic variants](https://mlsanity.com/paper/2109.14719/) (2021)
- [Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffs](https://mlsanity.com/paper/2305.18362/) (2023)
- [On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation](https://mlsanity.com/paper/1702.08670/) (2017)
- [Vine copula based knockoff generation for high-dimensional controlled variable selection](https://mlsanity.com/paper/2210.11196/) (2022)
- [DeepROCK: Error-controlled interaction detection in deep neural networks](https://mlsanity.com/paper/2309.15319/) (2023)

## Abstract (arXiv)

The deep neural network is a widely used framework in machine learning that has been widely applied in various fields. However, deep neural networks often involve a large number of parameters and inputs, many of which may be irrelevant to the goal or true output. These parameters and input variables not only increase computational complexity, but also contribute to additional computational cost. One solution to this problem is knockoff methods, which have proven successful in controlling false discovery rates in high-dimensional regression. Building on the knockoff methods and using the regularised neural network, this paper proposes three variable screening methods under the condition of controlling false discovery rates: one layer filter, multiple layers filter, and variable weight aggregation filter. In comparison with existing algorithms, we find that our algorithms show satisfactory performance.