ISSN :2582-9793

A Step Towards Global Counterfactual Explanations: Approximating the Feature Space Through Hierarchical Division and Graph Search

Original Research (Published On: 11-Aug-2021 )
A Step Towards Global Counterfactual Explanations: Approximating the Feature Space Through Hierarchical Division and Graph Search
DOI : 10.54364/AAIML.2021.1107

Maximilian Becker

Adv. Artif. Intell. Mach. Learn., 1 (2):94-114

Maximilian Becker : Vision and Fusion Lab, Institute for Anthropomatics and Robotics, Karlsruhe Institute of Technology (KIT), Germany.

Download PDF Here

DOI: 10.54364/AAIML.2021.1107

Article History: Received on: 05-Jul-21, Accepted on: 01-Aug-21, Published on: 11-Aug-21

Corresponding Author: Maximilian Becker

Email: MAXIMILIAN.BECKER@KIT.EDU

Citation: Maximilian Becker, Nadia Burkart, Pascal Birnstill, Jürgen Beyerer (2021). A Step Towards Global Counterfactual Explanations: Approximating the Feature Space Through Hierarchical Division and Graph Search. Adv. Artif. Intell. Mach. Learn., 1 (2 ):94-114

          

Abstract

    

The field of Explainable Artificial Intelligence (XAI) tries to make learned models more understandable. One type of explanation for such models are counterfactual explanations. Counterfactual explanations explain the decision for a specific instance, the factual, by providing a similar instance which leads to a different decision, the counterfactual. In this work a new approaches around the idea of counterfactuals was developed. It generates a data structure over the feature space of a classification problem to accelerate the search for counterfactuals and augments them with global explanations. The approach maps the feature space by hierarchically dividing it into regions which belong to the same class. It is applicable in any case where predictions can be generated for input data, even without direct access to the model. The framework works well for lower-dimensional problems but becomes unpractical due to high computation times at around 12 to 15 dimensions. 

Statistics

   Article View: 735
   PDF Downloaded: 10