Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks
2026-06-03 • Machine Learning
Machine Learning
AI summaryⓘ
The authors address the problem that deep neural networks often have many irrelevant parameters and inputs, making them slow and costly to run. They build on a technique called knockoff methods, which help identify important variables while controlling for false discoveries. The paper introduces three new variable screening methods that work with neural networks and help pick out relevant inputs without increasing errors. Their methods perform well compared to existing approaches.
deep neural networksvariable screeningfalse discovery rateknockoff methodsregularized neural networkhigh-dimensional regressionfeature selectioncomputational complexitymachine learning
Authors
Huiqi Zhang, Wenyu Liao, Yiqing Shi, Xiaobo Huang, Fang Xie
Abstract
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 \textcolor{black}{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: \textit{one layer filter}, \textit{multiple layers filter}, \textit{variable weight aggregation filter}. In comparison with existing algorithms, we find that our algorithms show satisfactory performance.