Skip to content
forked from gcskoenig/dipd

Disentangling Interactions and Dependencies in Feature Attribution using the DIP decomposition.

License

Notifications You must be signed in to change notification settings

tml-tuebingen/dipd

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

50 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DIP Decomposition

This package implements the DIP method (details and link to the paper will follow soon).

Installation

So far the package is not on pypi. You can download and install the package locally using pip. Clone the repository to your device, and in the folder into which you cloned the repo run the following command.

pip install dipd/

We recommend using python 3.11.7.

About

Disentangling Interactions and Dependencies in Feature Attribution using the DIP decomposition.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%