NIMO: a Nonlinear Interpretable MOdel

TL;DR

NIMO is a novel framework that combines the interpretability of linear models with the expressive power of neural networks, providing faithful and intelligible feature effects without sacrificing predictive accuracy.

Contribution

NIMO introduces an optimization method based on parameter elimination for neural networks that ensures inherent interpretability and flexibility.

Findings

Provides faithful and intelligible feature effects

Maintains competitive predictive performance

Incorporates sparsity through adaptive ridge regression

Abstract

Deep learning has achieved remarkable success across many domains, but it has also created a growing demand for interpretability in model predictions. Although many explainable machine learning methods have been proposed, post-hoc explanations lack guaranteed fidelity and are sensitive to hyperparameter choices, highlighting the appeal of inherently interpretable models. For example, linear regression provides clear feature effects through its coefficients. However, such models are often outperformed by more complex neural networks (NNs) that usually lack inherent interpretability. To address this dilemma, we introduce NIMO, a framework that combines inherent interpretability with the expressive power of neural networks. Building on the simple linear regression, NIMO is able to provide flexible and intelligible feature effects. Relevantly, we develop an optimization method based on parameter elimination, that allows for optimizing the NN parameters and linear coefficients effectively and efficiently. By relying on adaptive ridge regression we can easily incorporate sparsity as well. We show empirically that our model can provide faithful and intelligible feature effects while maintaining good predictive performance.