Can I read Generalized Integrated Gradients: A practical method for explaining diverse ensembles on EtoBox?

Generalized Integrated Gradients: A practical method for explaining diverse ensembles by Merrill, John; Ward, Geoff; Kamkar, Sean; Budzik, Jay; Merrill, Douglas is a scholarly article available to read on EtoBox.

What is Generalized Integrated Gradients: A practical method for explaining diverse ensembles about?

We introduce Generalized Integrated Gradients (GIG), a formal extension of the Integrated Gradients (IG) (Sundararajan et al., 2017) method for attributing credit to the input variables of a predictive model. GIG improves IG by explaining a broader variety of functions that arise from practical applications of ML in domains like financial services. GIG is constructed to overcome limitations of Shapley (1953) and Aumann-Shapley (1974), and has desirable properties when compared to other approaches. We prove GIG is the only correct method, under a small set of reasonable axioms, for providing explanations for mixed-type models or games. We describe the implementation, and present results of experiments on several datasets and systems of models.

Author

Merrill, John; Ward, Geoff; Kamkar, Sean; Budzik, Jay; Merrill, Douglas

Published

2019

Language

EN