GRIP2: A Robust and Powerful Deep Knockoff Method for Feature Selection

TL;DR

GRIP2 introduces a deep knockoff feature importance method that enhances robustness and power in feature selection, especially under high correlation and noise, with proven effectiveness on synthetic and real-world data.

Contribution

It develops a novel regularization-based importance statistic with efficient sampling, ensuring finite-sample FDR control and improved performance over existing methods.

Findings

Demonstrates robustness to feature correlation and noise.

Retains high power in low signal-to-noise regimes.

Successfully recovers known mutations in HIV data.

Abstract

Identifying truly predictive covariates while strictly controlling false discoveries remains a fundamental challenge in nonlinear, highly correlated, and low signal-to-noise regimes, where deep learning based feature selection methods are most attractive. We propose Group Regularization Importance Persistence in 2 Dimensions (GRIP2), a deep knockoff feature importance statistic that integrates first-layer feature activity over a two-dimensional regularization surface controlling both sparsity strength and sparsification geometry. To approximate this surface integral in a single training run, we introduce efficient block-stochastic sampling, which aggregates feature activity magnitudes across diverse regularization regimes along the optimization trajectory. The resulting statistics are antisymmetric by construction, ensuring finite-sample FDR control. In extensive experiments on synthetic and semi-real data, GRIP2 demonstrates improved robustness to feature correlation and noise level: in high correlation and low signal-to-noise ratio regimes where standard deep learning based feature selectors may struggle, our method retains high power and stability. Finally, on real-world HIV drug resistance data, GRIP2 recovers known resistance-associated mutations with power better than established linear baselines, confirming its reliability in practice.