Skip to content
This repository has been archived by the owner on Jul 18, 2024. It is now read-only.

Codes for reproducing the contrastive explanation in “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives”

License

Notifications You must be signed in to change notification settings

IBM/Contrastive-Explanation-Method

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Contrastive-Explanation-Method

Codes for reproducing the contrastive explanation in “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives

To find the pertinent positive (PP) of an instance,

python3 main.py -i 2953 --mode PP --kappa 10 --gamma 100

This would find the PP of image ID 2953 in the test images from the MNIST dataset.

From left to right: the original image and the pertinent positive component. This PP in Image 2953 is sufficient to be classified as 5.

To find the pertinent negative (PN) of an instance,

python3 main.py -i 340 --mode PN --kappa 10 --gamma 100

This would find the PN of image ID 340 in the test images from the MNIST dataset.

From left to right: the original image, the pertinent negative component and the image composed of the original image and PN. If we add PN to Image 340, it would be classified as 5.

The argument kappa (confidence lebel) and gamma (regularization coefficient of autoencoder) are tuning parameters for the optimization setup. Both PP and PN are used to explain the model prediction results. For more details, please refer to the paper.

About

Codes for reproducing the contrastive explanation in “Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives”

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages