Global Counterfactual Explanations: Investigations, Implementations and Improvements

04/14/2022
by   Dan Ley, et al.
0

Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, typically suggesting to aggregate masses of local explanations in the hope of ascertaining global properties, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are requesting more efficient and interactive explainability tools. We take this opportunity to investigate existing global methods, with a focus on implementing and improving Actionable Recourse Summaries (AReS), the only known global counterfactual explanation framework for recourse.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/26/2023

GLOBE-CE: A Translation-Based Approach for Global Counterfactual Explanations

Counterfactual explanations have been widely studied in explainability, ...
research
01/25/2023

Counterfactual Editing for Search Result Explanation

Recently substantial improvements in neural retrieval methods also bring...
research
01/06/2022

Topological Representations of Local Explanations

Local explainability methods – those which seek to generate an explanati...
research
08/02/2021

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

Counterfactual explanations provide means for prescriptive model explana...
research
10/30/2021

A Survey on the Robustness of Feature Importance and Counterfactual Explanations

There exist several methods that aim to address the crucial task of unde...
research
01/21/2020

Adequate and fair explanations

Explaining sophisticated machine-learning based systems is an important ...
research
11/21/2020

Explaining by Removing: A Unified Framework for Model Explanation

Researchers have proposed a wide variety of model explanation approaches...

Please sign up or login with your details

Forgot password? Click here to reset