NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning
This work addresses the need for interpretable and scalable models in high-risk domains, offering an incremental improvement over existing GAMs by integrating deep learning features.
The authors tackled the challenge of making deep learning models interpretable for high-risk applications like healthcare by proposing NODE-GAM and NODE-GA^2M, which scale better and achieve higher accuracy than other GAMs on large datasets while maintaining interpretability.
Deployment of machine learning models in real high-risk settings (e.g. healthcare) often depends not only on the model's accuracy but also on its fairness, robustness, and interpretability. Generalized Additive Models (GAMs) are a class of interpretable models with a long history of use in these high-risk domains, but they lack desirable features of deep learning such as differentiability and scalability. In this work, we propose a neural GAM (NODE-GAM) and neural GA$^2$M (NODE-GA$^2$M) that scale well and perform better than other GAMs on large datasets, while remaining interpretable compared to other ensemble and deep learning models. We demonstrate that our models find interesting patterns in the data. Lastly, we show that we improve model accuracy via self-supervised pre-training, an improvement that is not possible for non-differentiable GAMs.