NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning

Abstract

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.

arXiv comment2022 ICLR Spotlight paper

References in corpus (8)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Towards A Rigorous Science of Interpretable Machine Learning
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• InterpretML: A Unified Framework for Machine Learning Interpretability
• Concept Bottleneck Models
• Quasi-hyperbolic momentum and Adam for deep learning
• Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data
• Sparse Sequence-to-Sequence Models