SCIENCE@home

Tangentially Aligned Integrated Gradients for User-Friendly Explanations

Lachlan Simpson,Federico Costanza,Kyle Millar,A. Cheng,Cheng-Chew Lim,Hong-Gunn Chew

Published 2025 in Irish Conference on Artificial Intelligence and Cognitive Science

ABSTRACT

Integrated gradients is prevalent within machine learning to address the black-box problem of neural networks. The explanations given by integrated gradients depend on a choice of base-point. The choice of base-point is not a priori obvious and can lead to drastically different explanations. There is a longstanding hypothesis that data lies on a low dimensional Riemannian manifold. The quality of explanations on a manifold can be measured by the extent to which an explanation for a point lies in its tangent space. In this work, we propose that the base-point should be chosen such that it maximises the tangential alignment of the explanation. We formalise the notion of tangential alignment and provide theoretical conditions under which a base-point choice will provide explanations lying in the tangent space. We demonstrate how to approximate the optimal base-point on several well-known image classification datasets. Furthermore, we compare the optimal base-point choice with common base-points and three gradient explainability models.

PUBLICATION RECORD

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-29 of 29 references · Page 1 of 1

CITED BY

Showing 1-5 of 5 citing papers · Page 1 of 1