mlsanityData to 7 Oct 2026

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

arXiv 2606.04404 ↗First posted 3 Jun 2026stat.ML cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 3 Jun 2026.

Builds on

17 of 33 references.

References · 17

  1. 2015Training generative neural networks via Maximum Mean Discrepancy optimizationcited by 149
  2. 2016Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selectioncited by 120
  3. 2014Controlling the false discovery rate via knockoffscited by 97
  4. 2017Model Selection in Bayesian Neural Networks via Horseshoe Priorscited by 52
  5. 2018DeepPINK: reproducible feature selection in deep neural networkscited by 41
  6. 2018Deep Knockoffscited by 40
  7. 2020Efficient Variational Inference for Sparse Deep Learning with Theoretical Guaranteecited by 37
  8. 2020Consistent Feature Selection for Analytic Deep Neural Networkscited by 27
  9. 2016A knockoff filter for high-dimensional selective inferencecited by 25
  10. 2020Statistical Guarantees for Regularized Neural Networkscited by 25
  11. 2017Gene Hunting with Knockoffs for Hidden Markov Modelscited by 14
  12. 2022Sequential Attention for Feature Selectioncited by 9
5 more
  1. 2021Deep neural networks with controlled variable selection for the identification of putative causal genetic variantscited by 4
  2. 2023Statistically Significant Concept-based Explanation of Image Classifiers via Model Knockoffscited by 4
  3. 2017On architectural choices in deep learning: From network structure to gradient convergence and parameter estimationcited by 2
  4. 2022Vine copula based knockoff generation for high-dimensional controlled variable selectioncited by 1
  5. 2023DeepROCK: Error-controlled interaction detection in deep neural networkscited by 1

Built on by

Not cited yet.