Consistent feature selection for neural networks via Adaptive Group Lasso
This work addresses the need for interpretable neural networks in medical and engineering sciences, though it is incremental as it builds on existing regularization methods with added theoretical guarantees.
The authors tackled the interpretability problem in deep learning by proposing a feature selection method using adaptive group lasso for neural networks, establishing theoretical consistency and demonstrating applicability through simulations and data analysis.
One main obstacle for the wide use of deep learning in medical and engineering sciences is its interpretability. While neural network models are strong tools for making predictions, they often provide little information about which features play significant roles in influencing the prediction accuracy. To overcome this issue, many regularization procedures for learning with neural networks have been proposed for dropping non-significant features. Unfortunately, the lack of theoretical results casts doubt on the applicability of such pipelines. In this work, we propose and establish a theoretical guarantee for the use of the adaptive group lasso for selecting important features of neural networks. Specifically, we show that our feature selection method is consistent for single-output feed-forward neural networks with one hidden layer and hyperbolic tangent activation function. We demonstrate its applicability using both simulation and data analysis.