DeepAI AI Chat
Log In Sign Up

Geometrically Guided Integrated Gradients

by   Md Mahfuzur Rahman, et al.

Interpretability methods for deep neural networks mainly focus on the sensitivity of the class score with respect to the original or perturbed input, usually measured using actual or modified gradients. Some methods also use a model-agnostic approach to understanding the rationale behind every prediction. In this paper, we argue and demonstrate that local geometry of the model parameter space relative to the input can also be beneficial for improved post-hoc explanations. To achieve this goal, we introduce an interpretability method called "geometrically-guided integrated gradients" that builds on top of the gradient calculation along a linear path as traditionally used in integrated gradient methods. However, instead of integrating gradient information, our method explores the model's dynamic behavior from multiple scaled versions of the input and captures the best possible attribution for each input. We demonstrate through extensive experiments that the proposed approach outperforms vanilla and integrated gradients in subjective and quantitative assessment. We also propose a "model perturbation" sanity check to complement the traditionally used "model randomization" test.


page 6

page 7

page 8

page 14

page 15

page 16

page 18

page 19


Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Integrated gradients as an attribution method for deep neural network mo...

Investigating Saturation Effects in Integrated Gradients

Integrated Gradients has become a popular method for post-hoc model inte...

Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

Integrated Gradients (IG) is a commonly used feature attribution method ...

Pattern-Guided Integrated Gradients

Integrated Gradients (IG) and PatternAttribution (PA) are two establishe...

Compensated Integrated Gradients to Reliably Interpret EEG Classification

Integrated gradients are widely employed to evaluate the contribution of...

IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients

Integrated Gradients (IG) as well as its variants are well-known techniq...

Do Input Gradients Highlight Discriminative Features?

Interpretability methods that seek to explain instance-specific model pr...