Global Explanations of Neural Networks: Mapping the Landscape of Predictions

TL;DR

This paper introduces GAM, a method for generating global explanations of neural networks that reveal how predictions vary across subpopulations, enhancing interpretability and trust.

Contribution

GAM provides a novel approach for global explanations that identify subpopulations and their associated feature attributions, improving interpretability over existing methods.

Findings

GAM accurately recovers feature importances in simulated data

GAM's explanations align with statistical models on real data

Practitioners find GAM explanations intuitive

Abstract

A barrier to the wider adoption of neural networks is their lack of interpretability. While local explanation methods exist for one prediction, most global attributions still reduce neural network decisions to a single set of features. In response, we present an approach for generating global attributions called GAM, which explains the landscape of neural network predictions across subpopulations. GAM augments global explanations with the proportion of samples that each attribution best explains and specifies which samples are described by each attribution. Global explanations also have tunable granularity to detect more or fewer subpopulations. We demonstrate that GAM's global explanations 1) yield the known feature importances of simulated data, 2) match feature weights of interpretable statistical models on real data, and 3) are intuitive to practitioners through user studies. With more transparent predictions, GAM can help ensure neural network decisions are generated for the right reasons.