DeepAI AI Chat
Log In Sign Up

DisCERN:Discovering Counterfactual Explanations using Relevance Features from Neighbourhoods

by   Nirmalie Wiratunga, et al.
Robert Gordon University

Counterfactual explanations focus on "actionable knowledge" to help end-users understand how a machine learning outcome could be changed to a more desirable outcome. For this purpose a counterfactual explainer needs to discover input dependencies that relate to outcome changes. Identifying the minimum subset of feature changes needed to action an output change in the decision is an interesting challenge for counterfactual explainers. The DisCERN algorithm introduced in this paper is a case-based counter-factual explainer. Here counterfactuals are formed by replacing feature values from a nearest unlike neighbour (NUN) until an actionable change is observed. We show how widely adopted feature relevance-based explainers (i.e. LIME, SHAP), can inform DisCERN to identify the minimum subset of "actionable features". We demonstrate our DisCERN algorithm on five datasets in a comparative study with the widely used optimisation-based counterfactual approach DiCE. Our results demonstrate that DisCERN is an effective strategy to minimise actionable changes necessary to create good counterfactual explanations.


Algorithmic Recourse: from Counterfactual Explanations to Interventions

As machine learning is increasingly used to inform consequential decisio...

Robust Counterfactual Explanations for Tree-Based Ensembles

Counterfactual explanations inform ways to achieve a desired outcome fro...

GeCo: Quality Counterfactual Explanations in Real Time

Machine learning is increasingly applied in high-stakes decision making ...

Counterfactual Explanations for Concepts in ℰℒℋ

Knowledge bases are widely used for information management on the web, e...

Change Surfaces for Expressive Multidimensional Changepoints and Counterfactual Prediction

Identifying changes in model parameters is fundamental in machine learni...

On the Robustness of Counterfactual Explanations to Adverse Perturbations

Counterfactual explanations (CEs) are a powerful means for understanding...

Interpreting Process Predictions using a Milestone-Aware Counterfactual Approach

Predictive process analytics often apply machine learning to predict the...