Deep-gKnock: nonlinear group-feature selection with deep neural network
This addresses the problem of interpretable and reproducible feature selection for researchers in fields with grouped data, though it is incremental as it extends existing techniques to nonlinear settings.
The paper tackled nonlinear group-feature selection in high-dimensional data by combining deep neural networks with Knockoffs, achieving superior power and accurate group-wise False Discovery Rate control compared to state-of-the-art methods.
Feature selection is central to contemporary high-dimensional data analysis. Grouping structure among features arises naturally in various scientific problems. Many methods have been proposed to incorporate the grouping structure information into feature selection. However, these methods are normally restricted to a linear regression setting. To relax the linear constraint, we combine the deep neural networks (DNNs) with the recent Knockoffs technique, which has been successful in an individual feature selection context. We propose Deep-gKnock (Deep group-feature selection using Knockoffs) as a methodology for model interpretation and dimension reduction. Deep-gKnock performs model-free group-feature selection by controlling group-wise False Discovery Rate (gFDR). Our method improves the interpretability and reproducibility of DNNs. Experimental results on both synthetic and real data demonstrate that our method achieves superior power and accurate gFDR control compared with state-of-the-art methods.