Compensated Integrated Gradients to Reliably Interpret EEG Classification

11/21/2018
by   Kazuki Tachikawa, et al.
0

Integrated gradients are widely employed to evaluate the contribution of input features in classification models because it satisfies the axioms for attribution of prediction. This method, however, requires an appropriate baseline for reliable determination of the contributions. We propose a compensated integrated gradients method that does not require a baseline. In fact, the method compensates the attributions calculated by integrated gradients at an arbitrary baseline using Shapley sampling. We prove that the method retrieves reliable attributions if the processes of input features in a classifier are mutually independent, and they are identical like shared weights in convolutional neural networks. Using three electroencephalogram datasets, we experimentally demonstrate that the attributions of the proposed method are more reliable than those of the original integrated gradients, and its computational complexity is much lower than that of Shapley sampling.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/22/2020

Understanding Integrated Gradients with SmoothTaylor for Deep Neural Network Attribution

Integrated gradients as an attribution method for deep neural network mo...
research
03/25/2021

Symmetry-Preserving Paths in Integrated Gradients

We provide rigorous proofs that the Integrated Gradients (IG) attributio...
research
09/04/2019

Generalized Integrated Gradients: A practical method for explaining diverse ensembles

We introduce Generalized Integrated Gradients (GIG), a formal extension ...
research
10/23/2020

Investigating Saturation Effects in Integrated Gradients

Integrated Gradients has become a popular method for post-hoc model inte...
research
09/27/2017

Case Study: Explaining Diabetic Retinopathy Detection Deep CNNs via Integrated Gradients

In this report, we applied integrated gradients to explaining a neural n...
research
07/21/2020

Pattern-Guided Integrated Gradients

Integrated Gradients (IG) and PatternAttribution (PA) are two establishe...
research
04/03/2020

Attribution in Scale and Space

We study the attribution problem [28] for deep networks applied to perce...

Please sign up or login with your details

Forgot password? Click here to reset