Four Axiomatic Characterizations of the Integrated Gradients Attribution Method

Daniel Lundstrom

Abstract:

Deep neural networks have produced significant progress among machine learning models
in terms of accuracy and functionality, but their inner workings are still largely unknown.
Attribution methods seek to shine a light on these “black box” models by indicating how
much each input contributed to a model’s outputs. The Integrated Gradients (IG) method is
a state of the art baseline attribution method in the axiomatic vein, meaning it is designed to
conform to particular principles of attributions. We present four axiomatic characterizations
of IG, establishing IG as the unique method satisfying four different sets of axioms.